The news had spread fast. Ever since her essay, "The Texture of Time," was published in the alumni magazine, her phone hadn't stopped buzzing. Amelia had stopped answering it. She spent the entire day inside, curtains drawn, the silence only broken by the frantic chirping of her pet parakeet.

She paced the length of her living room, feeling trapped by her own words. Every memory from the essay played in her mind: the smell of the bakery, the crackling of the fireplace. She felt overwhelmed. She wrapped her arms around herself, as if trying to physically contain the intensity of her emotions, as the sun went down and the shadows stretched long across the walls. She went back to reading the essay, hoping to find a hint of calm.

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