"Are you sure this is the address?" Maya's voice, usually bright, was now muted, barely audible above the city’s din. She gripped the wallet, its weight an unwelcome reminder of her predicament. The woman's identification, a photo, beamed back at her, a cheerful smile. Maya felt her cheeks burning.

She rang the doorbell, heart racing. Each tick of the seconds stretched into an eternity. Her hands were clammy. She’d rehearsed what she would say, but now the words felt foreign, clunky.

When the door finally opened, Maya felt exposed, like an actress onstage without a script. A woman, her face pinched with worry, peered at her. Maya fumbled with the wallet, her fingers clumsy and unsure.

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