Maria felt a knot tighten in her throat as she scrolled through the feed. Liam’s feed. Liam, her sweet, quiet son, who spent most of his time gaming in his room. This account was a different story.

Her gaze kept darting to the mirror in the hallway. Her clothes, even the ones she'd carefully selected that morning, felt wrong, ill-fitting. The way she had her hair up, it seemed severe, like a teacher.

She found a photo of Liam at a party, surrounded by friends she'd never met. He was laughing, looking… free. A wave of something akin to shame washed over her as she thought of her own recent actions. She hadn't even talked to Liam today. She should have gone outside.

She abruptly shut the laptop, a sudden need to be away from it taking over. She headed towards the kitchen, but she quickly turned back. Maybe she should go change first.

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