The afternoon sun, ordinarily welcome, felt like an interrogator's spotlight. "It's really only fair," Mr. Evans was saying, his voice a low, reasonable drone. "The branches are hanging over my roof, and they're causing problems." I stared at the man, but my vision wouldn't focus. I felt a pressure in my chest. My breath hitched, a tiny gasp, as if a hand had reached inside me and squeezed.

I took a step back, instinctively. The trees, my trees, were what separated me from the outside world. I bit the inside of my cheek. "Let me think about it," I said, my voice barely audible.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198