Language-Specific Representation of Emotion-Concept Knowledge Causally Supports Emotion Inference
This provides a proof-of-concept that LLMs can learn about emotions without sensory-motor inputs, highlighting the role of language-derived knowledge in emotion inference, which is incremental as it builds on existing AI and psychology research.
The study investigated whether language-based representations of emotion causally contribute to AI's ability to infer emotions in novel situations, using large language models (LLMs). It found that 14 attributes of human emotion concept representation are encoded in distinct artificial neuron populations, and manipulating these neurons demonstrated their role in generative emotion inference, with performance deterioration linked to attribute importance in human mental space.
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.