"Could you *try* to be a little quieter?" Clara asked, her voice tight, when she encountered the neighbor while collecting her mail. The man, all smiles and apologies, had the audacity to suggest she get used to it. The audacity!

Clara retreated to her apartment, feeling a pressure building in her chest. She grabbed her phone, scrolling through social media, looking for ammunition. She'd find something, some reason to discredit them.

She started a scathing review of the company that they'd hired. It did little to ease the tension.

Emotion: hateful

Cluster: Anger / Hostility
PC1 (Valence): -1.71 Negative
PC2 (Disposition): 2.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.553
S0.367
retali0.313
aggravated0.310
0.308
Suppressed:
la-0.334
own-0.310
optimistic-0.270
been-0.264
gradual-0.262