The crumpled manuscript sat on the bedside table, a pale blue beacon in the dim morning light. Sarah’s heart hammered against her ribs, a frantic little bird trapped in a cage. She’d found it yesterday, hidden under a stack of Stephen King novels. It was a novel, and the main character was… her. Or, at least, someone who shared her name, her job, her quirky habit of humming show tunes in the shower. Her cheeks burned. She pulled the duvet tighter, hiding.

Her husband, Mark, was still asleep, snoring softly. She considered pretending she hadn't seen it, just sliding it back under the novels. But the sight of it, the thought of its contents, was like a physical weight. Every interaction with Mark would now be tinged with a new, uncomfortable layer.

She pushed herself up, needing a distraction. The kitchen, then. Coffee, and pretending this hadn't happened.

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