The coffee cup trembled slightly in her hand, the liquid sloshing dangerously close to the rim. It was all so simple, on paper. A shared tree, a shared decision. But Sarah felt a knot tighten in her gut as Mr. Peterson outlined his plan. The tree, he claimed, was causing a blockage of sunlight and causing the dampness.

Sarah stared at the tree, her gaze a fixed and unblinking stare. She imagined the silence that might befall her garden, the loss of privacy. She had loved the privacy the tree had given her garden, a protective embrace against the outside world.

She felt a strange buzzing in her ears. Each word, a pinprick, each argument a subtle violation. "Of course," she said, her voice strained, "we should discuss it further."

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