The cookbook signing was a nightmare. Clara watched as people lined up to get their copies of "Taste of Tuscany," a book supposedly written by a famous chef. That chef had, conveniently, taken Clara's grandmother's cookbook and adapted it. The recipes were hers, or at least, her grandmother's.

She kept her distance, lurking at the edge of the crowd. Every smile, every word of praise, felt like a personal insult. She felt a burning in her cheeks, and her hands clenched and unclenched. She didn’t know what to do.

She retreated to a corner, feeling exposed and vulnerable. The aroma of garlic and basil, usually a comfort, now felt like a taunt.

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