My hands were clammy as I approached the professor. The red 'C-' glared up at me from the marked essay. A knot had tightened in my stomach. It wasn’t just the grade; it was the sheer disconnect between what I’d poured into the paper and what I’d received. I found myself scanning his face, searching for a hint of the reason. His eyes, though, were impassive, hidden behind thick-rimmed glasses.

I kept my voice even. “Professor Davies, could you explain the feedback? I really thought I understood the material.” My nails tapped a nervous rhythm against the edge of the desk. Every muscle in my body felt like it was primed to spring.

He gestured vaguely at the essay. "Read the comments, Ms. Evans. They’re quite clear." Each word from his mouth sharpened my senses. The hum of the fluorescent lights suddenly seemed deafening. I felt like I was observing everything from a great height, looking down on the unfolding scene with heightened awareness.

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