He had always been an enigma, shrouded in an air of quiet contemplation. Now, she understood the source of that quiet. The novel, tucked away in a dusty drawer, revealed a version of her that felt both familiar and alien. It was her, but filtered through his perspective. Amelia felt exposed.

The next day, walking the dog, she found herself deliberately choosing the scenic route. She was usually a creature of habit, but today, she was seeking out the most beautiful, most picturesque scenery.

She tried to laugh it off, but her throat felt tight. At the park, she chatted loudly with a stranger. Anything to fill the silence, the void where her usual self had been.

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