The seating chart was a cruel joke. He had to sit directly across from her. He fumbled with the napkin on his lap, attempting to fold it into a swan, or at least something other than the lumpy mess it was becoming.

The speeches had begun, and each word felt like a deliberate jab. He watched her across the table, carefully avoiding eye contact. She was animated, laughing at something the person beside her had said.

He felt the blood drain from his face. The air in the room seemed thick, suffocating. He excused himself, mumbling something about needing to use the restroom, but he just needed to escape the spotlight.

In the mirrored bathroom, he splashed cold water on his face, trying to calm the turmoil he felt. He stared at his reflection, a stranger in a familiar face.

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