Generation-based extraction yields superior emotion vectors in small LMs that localize in middle layers following a U-shaped curve and enable architecture-dependent steering with three distinct behavioral regimes.
Title resolution pending
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
-
Extracting and Steering Emotion Representations in Small Language Models: A Methodological Comparison
Generation-based extraction yields superior emotion vectors in small LMs that localize in middle layers following a U-shaped curve and enable architecture-dependent steering with three distinct behavioral regimes.