Mark walked into the school’s open house with a deliberate casualness, but inwardly his stomach was doing flip-flops. Seeing Mr. Davies again, a man who seemed to hold every youthful indiscretion in his memory, filled him with a quiet sort of unease. He hoped his son, Tom, hadn't told him anything about his father's less-than-stellar history with the school.

He scanned the room, avoiding eye contact, though he had to. He found Mr. Davies, and made a beeline for a table. The memory of a certain history test that he had failed filled his mind.

“So, Mark, right?” Mr. Davies greeted him with a knowing smile. Mark winced, a tiny shudder running through him. He forced a smile. He was starting to sweat.

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