She grabbed her purse, the leather handle digging into her palm, and stormed out of the bookstore. She didn't bother to say goodbye to the man standing behind the counter, who’d been so polite to her, and so oblivious to who she was. She had just driven for hours, and now she just wanted to get home.

The bell above the door chimed, a cheerful sound that grated on her nerves. The sunlight felt too bright, the air too clean. She walked to her car, and started the engine. The car roared to life, a sound that felt more honest than the false smiles of the past hour.

He didn't recognize her. After all these years, he didn't even *remember* her.

She drove, faster and faster, letting the speed push the frustration. The scenery blurred into a stream of color. She was not going back.

Emotion: mad

Cluster: Anger / Hostility
PC1 (Valence): -1.94 Negative
PC2 (Disposition): 1.26

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.448
0.344
est0.340
🤬0.336
aggravated0.332
Suppressed:
a-0.495
de-0.485
la-0.387
H-0.344
latter-0.290