The spreadsheet blurred before Amelia's eyes. Each cell, a tiny prison. She chewed the inside of her cheek, a familiar habit whenever deadlines loomed. This project was critical, and Mr. Henderson's constant hovering wasn't helping. She felt the pressure building in her chest, a knot she couldn't seem to loosen.

"Amelia, you almost done with those quarterly reports?" Mr. Henderson's voice, chirpy as a summer bird, made her jump.

"Almost, sir," she managed, her voice a little too high. She needed to escape, even for a moment. Suddenly, she saw it: a small, faded picture on his desk. A cabin, a lake, and a familiar, goofy-looking kid wearing an oversized life jacket.

"Is that... Camp Woodchuck?" she blurted out, surprised.

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