Sweat trickled down the back of his neck, despite the air conditioning. He ran a hand through his hair, finding it plastered against his forehead. The waiting room music was a terrible distraction, a bland tune that grated on his nerves.

His name was called. He almost didn't hear it. But he rose, his muscles protesting with each movement.

The door opened and there she was, the girl who had made his life a misery. The bully. The one who had always seemed to know how to get under his skin.

โ€œPlease, come in, Alex,โ€ she said, gesturing toward the interior of the office. Her voice was smooth, but he could feel the tremors in his stomach.

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
๐Ÿ˜ฐ0.191
๋А๊ปด0.183
๐Ÿ˜ฃ0.183
๐Ÿ˜–0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198