The meeting was dragging. Ben fidgeted, adjusting his tie, pulling at his collar. He hated these presentations; the pressure to perform always felt immense. His palms were slick, and he could barely focus on the CEO's monotone voice. He longed to be anywhere else.

Then, across the table, his coworker, Emily, casually mentioned the archery tournament they held at the last company retreat. She’d been surprisingly good, he recalled. His mind flickered back to a memory, a specific bow, a specific target, and the camp they both attended.

"Emily," he said suddenly, the words leaving his mouth before he could stop them. "Did you ever go to Camp Clearwater?"

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
πŸ˜–0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198