It was the way Ms. Ramirez smiled in the hallways. The same, seemingly genuine smile she gave all of her students. Now, seeing her name among her followers, Sarah felt something inside her curdle. It wasn't the smile itself; it was the deception.

She had posted a picture the previous night, of her and her friends, laughing. A picture where she had thought she looked her best, carefree. Now, it felt tainted. Every laugh, every pose, every perfectly angled selfie felt, in retrospect, like a performance.

In class, Sarah ignored Ms. Ramirez's questions, doodling furiously in her notebook. She’d make sure the woman realized she wasn't so easily fooled. She could feel a heavy weight on her chest, a constant pressure that made her want to run.

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