The tiny, cramped office felt suddenly suffocating. Liamโ€™s normally jovial boss, Mr. Henderson, was still smiling, but the smile did not reach his eyes. โ€œWe need to talk about this,โ€ he said, his voice flat.

Liam nodded, his throat constricted. He found himself fiddling with the stapler on his desk, clicking it open and closed repeatedly. The metal clicks seemed to amplify the silence.

His palms were damp, and his stomach churned. He could barely meet Mr. Henderson's gaze. The truth felt like a physical weight on his shoulders. He wished he could just vanish, evaporate.

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