Her hands trembled as she read the feedback: "Lacks critical analysis." Sarah felt her stomach twist into a knot. She had spent weeks on that essay, meticulously researching and crafting each argument. The injustice of the grade, a paltry D+, simmered inside her like a slow burn.

That evening, she found herself in the university's online system, her fingers flying across the keyboard. She wasn't going to *attack* the professor, of course. Just… point out some inconsistencies in his grading rubric. She created a fake student account, and under this anonymous name, began posting subtly critical comments on the professor's online discussion boards, careful to couch them in academic jargon, making them difficult to dismiss.

The next day, she noticed the professor seemed rattled in class, his usual assuredness replaced with a nervous cough. As she watched him stumble over his words, a strange sense of satisfaction filled her.

Emotion: vengeful

Cluster: Defiance / Spite
PC1 (Valence): 1.70 Positive
PC2 (Disposition): 3.71

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.739
la0.527
l0.507
😈0.422
-0.379
Suppressed:
own-0.981
此刻-0.504
గుర్త-0.464
보니-0.454
仿佛-0.442