Mark adjusted his glasses, peering at the document. The flickering light from the overhead bulb made the words dance on the page. He hated being in his grandfather's cluttered workshop, the smell of sawdust and old paint reminding him of all his own shortcomings. He'd promised to tidy the place up, but he'd spent the last hour lost in the past.

The letter. A typed draft of resignation from a prestigious architecture firm. His grandfather, a man of such apparent success, had written this. He read the words, the apologetic tone, the justifications. It was addressed to his old boss, whom Mark had just been introduced to the previous week.

His throat constricted. He felt suddenly ill-equipped for the small talk he’d had. The letter exposed a hidden layer of doubt, something that made him feel as if he was always under some impossible scrutiny. He quickly replaced the letter and made a mental note to clean the workshop later, to get away from these ghosts.

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