The phone rang. It was her mother. Sarah stared at the blinking screen, a sense of dread pooling in her stomach. She knew what was coming. The news, the calls, the questions - it was all too much.

She answered, her voice trembling. Her mother’s concerned questions were like tiny jabs. She didn't have answers. She didn't even have a plan.

After the call, she wrapped her arms around herself, trying to ward off the encroaching chill. She moved to the window, watching the rain streak down the glass. Each drop, it seemed, was mirroring her own inner turmoil. She felt a profound sense of isolation, alone in the midst of a storm.

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