The cafeteria buzzed with a low, anxious murmur. Chloe picked at her salad, unable to swallow more than a few bites. The food, usually a welcome distraction, now tasted like sawdust. She watched other students, their faces etched with the same uncertainty, the same fear.

She kept checking her phone, expecting a deluge of messages. Each vibration sent a jolt of anxiety through her. She felt like she was trapped in a pressure cooker, the steam rising.

She took a deep breath, trying to regain control. She knew she had to face the reality, make a plan. But for now, all she could manage was to sit there, and feel the cold knot forming in her gut.

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