The constant tapping of Sarah's foot under the desk was the only thing that seemed to break the silence. Michael found himself intensely focused on the sound, using it as a sort of counterpoint to his anxious thoughts.

He felt like his skin was stretched too tight. He kept re-reading the email from HR, searching for clues, for hints. He knew the announcement could come at any minute.

He attempted a casual conversation with Carol, but he cut himself off mid-sentence, the words catching in his throat. He just wanted it to be over. He needed to escape the office.

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