He adjusted his glasses, a nervous habit he’d developed over the years. Inside the trunk, amongst moth-eaten shawls, lay a stack of photographs. He'd always been told his grandfather was a stoic man, a pillar of the community. In the photo, his grandfather was surrounded by several women.

This man was younger, and he was grinning widely. It wasn’t the picture of the man he thought he knew. The man's arms were around his friends, their faces pressed close. The stories were of a reserved man who held his emotions in check.

A bead of sweat trickled down his temple. He felt a shiver run through his frame. All his life, he’d striven to emulate his grandfather. Now, he wasn't sure what to think.

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