Leo tightened the knot of his tie again, his fingers fumbling. He glanced at the overflowing coffee cup on the counter, then back at his phone. He'd just finished a grueling workout, and the endorphins had him feeling a little… vulnerable, to put it mildly. He'd been about to text Sarah, a friendly "Good morning!" when he realised it was actually addressed to his ex. Dread pooled in his stomach like a cold wave. He deleted the text, but the phantom vibration in his pocket made him jump. He checked the phone again; no new messages. He needed to leave for the interview, and the interview was important. He was sure his hands were shaking as he grabbed his briefcase.

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