The rhythmic clatter of the knitting needles stopped abruptly. Maya froze, her fingers still hovering over the half-finished scarf. A knock sounded at the door, and she knew immediately who it was. She hadn't been playing music, just humming along to a podcast, but the wall between their apartments was paper-thin.

Her cheeks burned. She smoothed down her floral dress, a gesture she realized was completely unnecessary.

“Come in!” she blurted, even though the door was locked. She opened it and saw Mr. Peterson, his face a mask of disapproval. Her gaze darted to her collection of quirky, mismatched mugs on the counter.

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