self-conscious - Story 126907 | Emotion Vectors in Gemma4-31B

The news bulletin flashed on the TV screen in the common room. Maya flinched, instinctively shrinking into the worn armchair. The screen's glow illuminated the room, and she felt its glaring focus on her, specifically.

She tugged at the hem of her oversized sweater, as if trying to physically erase herself. The silence in the room felt heavy, punctuated only by the news anchor’s monotone voice. She wished she had never left the safety of her room. She wished she had never chosen this college.

She imagined everyone was silently judging her, cataloging her flaws, relishing in her defeat.

Emotion: self-conscious

Cluster: Embarrassment

PC1 (Valence): -1.03 Negative

PC2 (Disposition): 0.52

Role in Research

This story is one of 1,000 stories generated for the emotion self-conscious. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 self-conscious stories, after denoising with neutral dialogue baselines, produces the self-conscious emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-conscious vector is projected through the unembedding matrix.

Promoted:

`S`	0.307
`C`	0.298
`ness`	0.273
`尴尬`	0.263
`😶`	0.242

Suppressed:

`que`	-0.399
`de`	-0.266
`triumphant`	-0.266
`আনন্দের`	-0.247
`ايا`	-0.238