The sun beat down on David’s back as he stood in the antique shop, sweat beading on his forehead. He clutched his grandfather's war medals in a worn leather case, the polished metal gleaming under the harsh light. He'd never liked being the center of attention.

The shop owner, a small, wizened woman with piercing eyes, was circling him slowly, like a predator eyeing its prey. David kept his gaze fixed on the floor, avoiding her scrutiny. Each moment felt like an eternity.

“So,” the woman said, her voice surprisingly soft. “Tell me about these.” David swallowed, his throat suddenly dry. He felt exposed, vulnerable. His voice was hoarse as he began to speak, the words catching in his throat, and he was barely audible.

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