He stared at his reflection, tugging at the collar of his shirt. It felt too tight. He’d practiced his opening jokes in the mirror, but now, he couldn't remember them. Liam’s comedy show at the local theater had been booked for weeks. This small gathering at the community center felt amateurish.

He could hear the distant roar of laughter from Liam’s party across town. Each car that drove past made him jump. Was someone leaving? Coming to his party?

When the first guest arrived, he felt a rush of relief, followed quickly by a wave of apprehension. He plastered a smile on his face, trying to appear relaxed, but his hands trembled as he offered a handshake. This was going to be a long night.

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