The attic stairs creaked under her weight. She hated this part, the climb, the inevitable feeling of being watched. She pulled a trunk towards her. Inside, a faded photo album. A younger version of her mother was in it, wearing a motorcycle jacket, a rebellious streak evident in her defiant pose.

Her mother's voice had always been hushed, soft, cautious. This photograph spoke a different language: a language of risk, adventure. She felt a familiar unease bloom in her chest. She had always been told she was the cautious one.

She flipped the page, her fingers trembling slightly. The difference between the carefully curated stories and this raw, untamed spirit was jarring. She felt a need to disappear, to shrink, to be invisible.

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