Eliza stared at the list. “Learn to speak Italian.” It was scrawled at the top, bold and ambitious. Her mother, a quiet woman, had always seemed content with her routine. Eliza, on the other hand, felt the weight of every perceived flaw, every misspoken word.

She pictured herself in a crowded piazza, trying to order pasta. Her accent, a clumsy jumble, would betray her, marking her as an outsider. Her cheeks warmed at the prospect. The thought of everyone hearing her butchered Italian was almost unbearable. She sighed, her gaze fixed on the list. Why did her mother have to leave this behind? Now she felt a sense of obligation.

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