Irrelevant angry faces impair response inhibition, and the go and stop processes share attentional resources

Abstract

Response inhibition is a crucial component of executive control, which refers to our ability to suppress responses that are no longer needed or inappropriate. The stop-signal task is a standard tool to assess inhibitory control over actions. Here, we use irrelevant facial expressions (happy, angry, or neutral) as both go and stop-signal to examine competition for shared attentional resources between (a) emotion and inhibition process and (b) go and stop processes. Participants were required to respond to go signals (gender discrimination task: male or female). Occasionally, a stop-signal (face with irrelevant angry, happy, or neutral facial expression) was presented, and participants were required to withhold their motor response. We found that emotion processing (especially angry faces) captures attention away from the task, and the emotionality of the stop signal matters only when the go signal is non-emotional. When the go signal was non-emotional, we found that stop-signal with irrelevant angry facial expressions impaired inhibitory control compared to stop-signal with irrelevant happy and neutral facial expressions. These results indicate that the processing of emotion and inhibition process exploit a shared pool of attentional resources. These results favor an interactive capacity-sharing account of the go and stop processes in models of response inhibition.

Figure 1

Schematic of Emotional Stop Signal Task. An example of a go and a stop trial. (a) During go trials, participants were required to press the left arrow key for male faces and the right arrow key for female faces. (b) During stop-trials, they were required to withhold their motor response (signaled by a face at the top of go face with irrelevant happy, angry, or neutral emotions). The stop-signal followed the go-signal after a variable time delay called stop-signal delay (SSD). The SSD was set based on a staircase procedure separately for each stop-signal condition to get stop-performance at approximately 50% correct.

Figure 2

(a) Stop-Signal Reaction Time: Go emotion. Stop signal reaction time (SSRT) for three go emotions. Error bars indicate the standard error of the corresponding means. The SSRT for the angry go signal was significantly higher than SSRT for the happy and neutral go signal (see text). ^** p < 0.001. (b) Box-plot distribution of a. Stop signal reaction time (SSRT) for three go emotions. The SSRT for the angry go signal was significantly higher than SSRT for the happy and neutral go signal (see text). ^**p < 0.001.

Figure 3

(a) Stop-Signal Reaction Time: Nine Conditions. Stop signal reaction time (SSRT) for nine conditions grouped as per the emotion of go signal (x-axis). Error bars indicate the standard error of the corresponding means. The legend shows three emotional stop signals. Under neutral go emotion, the SSRT was significantly higher for the angry face stop-signal compared to the happy face stop-signal (see text). ^*p < 0.05. (b) Box-plot distribution of a. Stop signal reaction time (SSRT) for stop-signal emotion conditions grouped across three go emotions. Under neutral go emotion, the SSRT was significantly higher for the angry face stop-signal compared to the happy face stop-signal (see text). ^*p < 0.05.

Figure 4

Noncancelled RT fitted with PPT. We fitted noncancelled RT and PPT data with an exponential function (noncancelled RT = εe^b(PPT) + c). We fixed ε at 17 ms (equal to one refresh duration of the display monitor). Coefficients ‘b’ and ‘c’ were fitting coefficients that varied across participants. The average (± SEM) of best fit across participants in three conditions is plotted as a function of PPT. The angry stop signal had the lowest attenuation rate.

Figure 5

Attenuation Rate for three Stop-signal. Attenuation rate, the measure of inhibitory control, is the coefficient b in exponential function (noncancelled RT = εe^b(PPT) + c). Boxplot of distributions of attenuation rate for three stop-signal conditions is shown. The average attenuation rate in the angry stop signal condition was lesser than in the happy stop-signal condition, indicating poor inhibitory control with angry faces. ^**p < 0.01.