The office felt suffocating. Every breath that came and went brought a wave of this awful feeling. He sat across from Michael, his replacement, and found himself wanting to push the table, to kick the chairs. The whole situation was an injustice.

“The first thing you have to learn is…” Thomas began, his voice flat and robotic. He felt the urge to just walk away, to leave him to his own devices.

Michael leaned forward, eager to learn. Thomas gave a curt instruction, then looked away, out the window, at the sky, anywhere but at the eager face across from him. He couldn’t look at him.

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