The cheap paper of the card felt flimsy in Leo's hands. A cartoon cat wearing a party hat stared back at him. He shoved it in his pocket, then pulled it back out. He was already late.

He kept glancing at the card as he rode the bus. He hated being late, but today, it felt like an excuse. He kept smoothing down his shirt, tugging at the collar, as if it were suddenly too tight. He was acutely aware of every bump in the road.

He finally found a moment to open the card at his desk, pretending to be preoccupied with a file. The message read: "Hope it's purr-fect!" Leo's face flushed. He crumpled the card in his fist, a sudden anger boiling inside him. He was sure it was a joke.

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