The phone rang again. It was the bank. Another collection call. This was the third one this week. I let the answering machine pick it up. My shoulders were tight, almost touching my ears. I felt trapped.

A pair of brown eyes peered at me through the gap in the fence. Buster. I sighed, the air hissing through my teeth.

He was, as usual, sniffing at my vegetable garden, his tail a blurry propeller. I felt the slow burn of anger creep up my neck. I couldn’t deal with this right now.

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