Differential Impact of Emotion on Semantic Processing of Abstract and Concrete Words: ERP and fMRI Evidence

Abstract

Emotional valence is known to influence word processing dependent upon concreteness. Whereas some studies point towards stronger effects of emotion on concrete words, others claim amplified emotion effects for abstract words. We investigated the interaction of emotion and concreteness by means of fMRI and EEG in a delayed lexical decision task. Behavioral data revealed a facilitating effect of high positive and negative valence on the correct processing of abstract, but not concrete words. EEG data yielded a particularly low amplitude response of the late positive component (LPC) following concrete neutral words. This presumably indicates enhanced allocation of processing resources to abstract and emotional words at late stages of word comprehension. In fMRI, interactions between concreteness and emotion were observed within the semantic processing network: the left inferior frontal gyrus (IFG) and the left middle temporal gyrus (MTG). Higher positive or negative valence appears to facilitate semantic retrieval and selection of abstract words. Surprisingly, a reversal of this effect occurred for concrete words. This points towards enhanced semantic control for emotional concrete words compared to neutral concrete words. Our findings suggest fine-tuned integration of emotional valence and concreteness. Specifically, at late processing stages, semantic control mechanisms seem to integrate emotional cues depending on the previous progress of semantic retrieval.

Figure 1

EEG concreteness effects. Average ERPs in the four ROIs. The difference maps were obtained by subtraction of the abstract from the concrete ERPs.

Figure 2

EEG emotion effects. Average ERPs in the four ROIs. The difference maps were obtained by subtraction of the neutral from the emotional ERPs.

Figure 3

Interaction concreteness * emotion in the EEG data. Average ERPs in the four ROIs. The difference maps were obtained by subtraction of the neutral from the emotional ERP measurements.

Figure 4

Interaction concreteness * emotion in the fMRI data, mean percent BOLD signal change. Regions surpassing the maximum activation proportion expected under the null hypothesis superimposed on a standard single subject brain. Error bars represent the standard error of the mean.