The attic air was thick with the scent of dust and forgotten things. Emily, usually so at ease, felt a strange pressure in her chest as she sifted through the boxes. Her mother's "memory lane," as she called it, was a treasure trove of humiliation.

There was the book report on a novel she’d clearly misunderstood. The science project on volcanoes that had, predictably, failed to erupt. The notes from a boy she'd had a crush on in fifth grade (the handwriting was the most painful part). She felt a prickly heat rise from her neck to her face.

She felt compelled to close the box. This wasn't her. This wasn't the competent woman who had built her career. This was an unearthed, preserved version of her vulnerabilities, and she didn’t want anyone to see it.

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