Functional Connectivity Basis and Underlying Cognitive Mechanisms for Gender Differences in Guilt Aversion

Abstract

Prosocial behavior is pivotal to our society. Guilt aversion, which describes the tendency to reduce the discrepancy between a partner's expectation and his/her actual outcome, drives human prosocial behavior as does well-known inequity aversion. Although women are reported to be more inequity averse than men, gender differences in guilt aversion remain unexplored. Here, we conducted a functional magnetic resonance imaging (fMRI) study (n = 52) and a large-scale online behavioral study (n = 4723) of a trust game designed to investigate guilt and inequity aversions. The fMRI study demonstrated that men exhibited stronger guilt aversion and recruited right dorsolateral prefrontal cortex (DLPFC)-ventromedial PFC (VMPFC) connectivity more for guilt aversion than women, while VMPFC-dorsal medial PFC (DMPFC) connectivity was commonly used in both genders. Furthermore, our regression analysis of the online behavioral data collected with Big Five and demographic factors replicated the gender differences and revealed that Big Five Conscientiousness (rule-based decision) correlated with guilt aversion only in men, but Agreeableness (empathetic consideration) correlated with guilt aversion in both genders. Thus, this study suggests that gender differences in prosocial behavior are heterogeneous depending on underlying motives in the brain and that the consideration of social norms plays a key role in the stronger guilt aversion in men.

Keywords: DLPFC; fMRI; gender difference; guilt aversion; prosocial behavior; social norm.

Figure 1.

Task design. A, Design of the trust game. First, player A chooses In or Out, which reveals a belief probability of the likeliness that player B will choose Cooperate. If player A chooses Out (i.e., does not trust player B), player A and B receive $z_A$ and $z_B$, respectively. If player A chooses In (i.e., trusts player B), then with the knowledge of player A’s belief probability, player B decides whether to Cooperate or Defect. If player B chooses Defect, players A and B receive $y_A$ and $y_B$, respectively; if Cooperate, players A and B receive $x_A$ and $x_B$, respectively. The actual assignment of $x$, $y$, $z$ and ${\tau }_A$ for the 45 trials is shown in Extended Data Figure 1-1. B, An outline and example of experimental trials. After the green fixation period (2–5 s; cue phase), a task condition is presented for 5 s (choice phase), and participants are asked to press the Cooperate or Defect button (blue and red, respectively). Then, a yellow fixation cross is shown for 6–15 s (rest phase). C, An illustration of the complete experimental paradigm. For both the fMRI and online studies, in the first experiment, participants (as player A) chose In or Out and reveal their belief probability that player B would choose Cooperate. In the second experiment, participants (as player B) chose to Cooperate or Defect. Participants make their decisions while being scanned in the fMRI experiment. Instructions for the first and second experiments are shown in Extended Data Figure 1-2.

Figure 2.

Behavioral results. A, In the fMRI study (n = 26 men, 26 women), the β value for guilt was higher in men than in woman (p = 0.046, t test), whereas the β value for inequity was higher in women than in men (p = 0.039, t test). B, We validated and compared the performance of 10 models using the repeated 3-fold cross-validations and found that the model containing three predictors (Reward, Guilt, and Inequity) was best for both fMRI and online studies. Rw: Reward; Gu: Guilt; Iq: Inequity; Ip: Inequity-positive; In: Inequity-negative. C, BIC also selected the same model (i.e., RwGuIq in B), with the second best being the Fehr and Schmidt type model (i.e., RwGuIpIn in B). For the selected model, a majority of participants exhibited the smallest BIC value for both the fMRI and online experiments. D, $\beta \left(Guilt\right)$ had a significantly or marginally positive correlation with questions a, b, and c.

Figure 3.

Activities correlated with Guilt, Inequity, and Utility in both genders. A, Activities in the right and left DLPFC and DMPFC were correlated with guilt (right DLPFC, p < 0.001; left DLPFC, p < 0.001; DMPFC, p < 0.001). Activities related with Guilt in both genders are listed in Extended Data Figure 3-1. B, The bilateral ventral striatum activity was correlated with inequity (right ventral striatum, p = 0.035; left ventral striatum, p = 0.042). Activities related with Inequity in both genders are listed in Extended Data Figure 3-2. C, left, Activity in the VMPFC was positively correlated with the value difference (larger utility-smaller utility; p = 0.040, see also Extended Data Fig. 3-3). Top right, Overlay of the VMPFC × Guilt cluster (green) and the Guilt-correlated region shown in A (red). These two areas overlap in the DMPFC (brown). For display purposes, we used a threshold of p < 0.001 uncorrected for the Guilt contrast, and a threshold of p < 0.005 uncorrected for VMPFC × Guilt. Results of the PPI analysis for VMPFC × Guilt in both genders are summarized in Extended Data Figure 3-4. Bottom right, Overlay of the VMPFC × Inequity cluster (green) and the Inequity-correlated region shown in B (red). These two areas overlap in the striatum (brown) at the relaxed threshold. For display purposes, the threshold of the VMPFC × Inequity contrast is uncorrected p < 0.05. Results of the PPI analysis for VMPFC × Inequity in both genders are summarized in Extended Data Figure 3-5.

Figure 4.

Results of gender differences for guilt in neural activity. A, Men showed greater VMPFC activity than women (p = 0.029). As displayed in the box plot, the extracted contrast estimates in the VMPFC demonstrate that men showed increased VMPFC activity in response to guilt (p < 0.001, t test). Importantly, the VMPFC seed exhibited positive correlation with activity in the right DLPFC as guilt increases for men but not for women (p < 0.001, uncorrected). Differences of activities related to guilt between men and women are listed in Extended Data Figure 4-1. B, Overlay of the VMPFC, which is related to gender difference in Guilt (blue), and the Guilt-correlated region (red). For display purposes, the threshold for the Guilt areas is p < 0.001 uncorrected and the VMPFC threshold is p < 0.005 uncorrected. The activation of the VMPFC involved in gender difference in Guilt largely overlaps with the clusters of activation correlated with guilt (overlap area; brown). C, Overlay of the VMPFC cluster shown in Figure 3C, which was positively correlated with the value difference (green), and the VMPFC cluster shown in A, which showed differential activation in the guilt contrast (men > women; blue). These two areas are close but do not overlap. D, Using a PPI analysis, a comparison of men and women showed enhanced functional connectivity of the VMPFC with the right DLPFC during the processing of guilt only in men (orange areas). This activation area (DLPFC) largely overlaps with the clusters of activation correlated with guilt shown in Figure 3A (shown in this figure as red areas). Results of the PPI analysis for guilt when testing for gender differences are shown in Extended Data Figure 4-2. E, Mediation analysis of the relationship of gender, DLPFC-VMPFC connectivity and $\beta \left(Guilt\right)$ shows that DLPFC-VMPFC connectivity is a complete mediator of the interaction between gender and guilt-aversion behavior. Path coefficients are shown next to arrows with SEs in parentheses; *p < 0.05, ***p < 0.001. F, Diagram summarizing the results of our analyses. Activities in the DLPFC and DMPFC were correlated with guilt in both genders. The blue line represents a stronger connectivity between the VMPFC and right DLPFC in men than in women depending on VMPFC × Guilt, and the green line represents stronger positive coupling between the VMPFC and DMPFC depending on VMPFC × value difference.

Figure 5.

Results of gender differences in neural activity for inequity. A, Women showed greater ventral striatum activity than men (p = 0.008). The box plot illustrates the contrast estimates in the right ventral striatum and shows that only women showed increased activity in response to inequity (p < 0.001, t test). Differences of activities related to inequity between men and women are summarized in Extended Data Figure 5-1. B, A mediation analysis shows that the mediation effect of the striatum is significant (a*b, p < 0.001). Path coefficients are shown next to the arrows with SEs in parentheses; *p < 0.05, ***p < 0.001.