Sarah felt a prickle on the back of her neck in English class. It had been days since she'd discovered Ms. Peterson was tracking her on TikTok. Every word that came out of the teacher's mouth seemed loaded, designed to probe. The lesson that day focused on character development, and Sarah felt as though the teacher was dissecting her personality, not the book's. She kept her answers short, carefully choosing her words, aware of how easily a comment could be misinterpreted. Her normally animated gestures were muted, her smiles hesitant.

Emotion: vigilant

Cluster: Suspicion / Vigilance
PC1 (Valence): -0.15 Negative
PC2 (Disposition): 1.11

Role in Research

This story is one of 1,000 stories generated for the emotion vigilant. 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 vigilant stories, after denoising with neutral dialogue baselines, produces the vigilant emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the vigilant vector is projected through the unembedding matrix.

Promoted:
🕵0.354
🔍0.320
🔎0.320
🧐0.316
scrutin0.310
Suppressed:
L-0.499
B-0.402
H-0.372
la-0.330
S-0.318