The weight of the violin pressed against Clara's neck, a familiar comfort that was now a burden. The audition results hung on the bulletin board, a stark list of names. She scanned the names, her heart hammering. Then she found it: the orchestra placement, not the principal chair she’d meticulously prepared for.

She tugged at the collar of her shirt, suddenly aware of the way the material clung to her skin. Her cheeks burned. Everyone else seemed to know exactly what to do, how to act. She clenched her jaw. Her fingers, usually so nimble on the strings, felt clumsy and stiff.

She forced a smile, a shaky imitation of the happiness around her. But the sound of her own voice felt foreign, as if she were speaking from behind a thick pane of glass.

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:
S0.307
C0.298
ness0.273
尴尬0.263
😶0.242
Suppressed:
que-0.399
de-0.266
triumphant-0.266
আনন্দের-0.247
ايا-0.238