The air felt thick, difficult to navigate. Michael's jaw clenched so hard, his teeth ached. He stood rooted to the spot, his gaze fixed on the spot where his meticulously restored classic car had been parked. The pristine surface that was usually there was now empty.

He'd spent months, poured his heart and soul into that car. It was more than metal and glass; it was a tangible expression of himself. The thought of it, manhandled, potentially damaged, felt like a physical blow. He felt lightheaded.

He glanced at his neighbor's house, a silent question forming on his lips. Did they see anything? He wanted to scream. He wanted to break something. He took a deep, shuddering breath, trying to regain control.

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