LLMs encode jealousy as a linear combination of superiority and relevance factors consistent with human psychology, allowing mechanical detection and suppression of toxic states.
Mechanistic interpretability of emotion inference in large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Mechanistic Decoding of Cognitive Constructs in Large Language Models
LLMs encode jealousy as a linear combination of superiority and relevance factors consistent with human psychology, allowing mechanical detection and suppression of toxic states.