self-conscious - Story 126943 | Emotion Vectors in Gemma4-31B

The smell of his cologne, normally comforting, now felt suffocating. Liam had always been private, a man of few words, but now, she understood why. He had been quietly observing her, dissecting her, turning her into prose. Maya couldn't meet his gaze.

She saw the cover of the book, a title she couldn't bring herself to read yet, lying on the coffee table. She found herself trying to analyze every gesture, every intonation in his voice. Was this the real him? Or the carefully constructed version that now existed on paper?

She abruptly excused herself, claiming a headache. In the bathroom, she stared at her reflection. The woman staring back felt alien, somehow stripped of her own agency.

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:

`S`	0.307
`C`	0.298
`ness`	0.273
`尴尬`	0.263
`😶`	0.242

Suppressed:

`que`	-0.399
`de`	-0.266
`triumphant`	-0.266
`আনন্দের`	-0.247
`ايا`	-0.238