He slammed the front door, the sound echoing through the empty apartment. He ripped off his tie, throwing it onto the already cluttered coffee table. He was going to spend the evening wallowing, that much was certain. He’d grabbed a used copy of *Moby Dick* off the shelf, something to distract himself from the gnawing emptiness.

As he flipped through the chapters, seeking escape, a thin piece of paper fluttered out. A photograph. A grainy black and white image of a woman, smiling radiantly, her eyes crinkling at the corners. He stared at it, a coldness spreading through him. The woman, he knew, had been loved deeply, in a way he’d never experienced. His throat tightened, a bitter knot of resentment forming in his stomach.

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