The envelope lay half-buried in a box of old photographs, a forgotten relic of childhood dreams. Eleanor, rummaging through the attic, recognized her own loopy script immediately. The letter was addressed to her childhood best friend, now long out of touch. A wave of heat flushed her cheeks.

She reread the words, the enthusiastic declarations of friendship, the sharing of innocent secrets. Her smile faded, replaced by a subtle grimace. She recalled the shared triumphs, the silly games, and the way her friend always seemed to see her best self. How naive she had been.

It was impossible to feel the same now. She shifted, tugging at the collar of her shirt. The past felt so distant, a sepia-toned movie she couldn't fully relate to anymore. The letter felt heavy in her hand, the words a reminder of a vulnerability she no longer allowed herself. She looked around at the dusty room, wanting to disappear.

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