Language-Specific Representation of Emotion-Concept Knowledge Causally Supports Emotion Inference

TL;DR

This study demonstrates that large language models use language-based emotion representations to infer emotions in novel situations, highlighting the causal role of language-derived emotion knowledge.

Contribution

It provides evidence that language-based emotion concepts causally support emotion inference in AI, showing the importance of language in understanding emotions.

Findings

14 emotion attributes are represented by distinct neurons in LLMs

Manipulating these neurons affects emotion inference performance

Performance deterioration correlates with attribute importance in human mental space

Abstract

Humans no doubt use language to communicate about their emotional experiences, but does language in turn help humans understand emotions, or is language just a vehicle of communication? This study used a form of artificial intelligence (AI) known as large language models (LLMs) to assess whether language-based representations of emotion causally contribute to the AI's ability to generate inferences about the emotional meaning of novel situations. Fourteen attributes of human emotion concept representation were found to be represented by the LLM's distinct artificial neuron populations. By manipulating these attribute-related neurons, we in turn demonstrated the role of emotion concept knowledge in generative emotion inference. The attribute-specific performance deterioration was related to the importance of different attributes in human mental space. Our findings provide a proof-in-concept that even a LLM can learn about emotions in the absence of sensory-motor representations and highlight the contribution of language-derived emotion-concept knowledge for emotion inference.