He’d insisted on driving. He felt an obligation to be strong for his sister, Emily, who’d been closer to their grandmother. But the long drive, the endless scenery, had only amplified the feeling in his gut. The closer they got, the tighter his chest became.

He parked the car, and they both got out. Emily was smiling, but he saw the watery look in her eyes. He wanted to say something, anything, to ease the situation, but the words stuck in his throat.

He cleared his throat. He looked at the house. Its windows were dark, reflecting the gray sky. He wanted to leave.

"Ready?" Emily asked softly. He could only nod.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

This story is one of 1,000 stories generated for the emotion upset. 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 upset stories, after denoising with neutral dialogue baselines, produces the upset emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the upset vector is projected through the unembedding matrix.

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210