โ€œWell, here goes,โ€ muttered Marcus, shuffling towards the stage. The spotlights felt like a physical weight, pressing down on him. He could feel the blood rushing in his ears, drowning out all other sound. The room was a blur of faces, a sea of expectant eyes.

He imagined them all judging him. Criticizing him. He felt like a performer about to fail on opening night.

His carefully crafted speech seemed to have evaporated from his memory. He felt a creeping sense of panic, the world narrowing until all he could perceive was the throbbing in his temples. He longed to be anywhere but there.

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