"Did you hear?" Chloe's voice sliced through the nervous energy in the dorm room. I fiddled with the frayed edges of my favorite scarf. The news hung in the air, a heavy, unwelcome guest. I forced a smile, but it felt brittle, thin.

My hands felt clammy. I instinctively smoothed down my jeans, as if that would somehow remedy the situation. The world felt smaller, more cramped. The colorful posters on the wall seemed to mock me.

"I don't know what I'm going to do," I confessed, my voice barely a whisper. I avoided Chloe's gaze, afraid to see pity or – even worse – indifference. The impending closure felt like a colossal mistake on my part, even though it wasn't.

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