Eliza’s hands wouldn't stop fidgeting. She twisted and turned the cheap plastic pen the hospital had provided, the clicking a metronomic beat that only added to her growing despair. The clinic's sterile environment seemed to amplify her unease. The information had settled over her like a suffocating blanket.

She kept replaying the doctor’s serious, measured tone in her mind. That slow, measured way of talking had never felt so ominous. The air in the small room felt heavy, and the silence seemed to grow with each passing second. She felt a burning sensation in her chest, the pain of knowing.

She pressed her palms together, squeezing tightly. She closed her eyes, trying to force herself to calm down, but it was useless. The facts of the situation were unyielding. She felt a wave of nausea wash over her.

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