The accusation felt like a slap in the face. Sarah, a model student, was accused of lifting content from a research paper. The accuser, Professor Davies, had a smug look about him, which fueled a burning sensation in Sarah's chest.

She decided to fight back. Her response? A meticulous audit of every single one of Davies' past publications. Every footnote, every citation, was scrutinized. Sarah, usually a champion of integrity, found herself relishing the prospect of uncovering any imperfections, any small slip-ups that she could exploit.

Days bled into weeks as Sarah spent her evenings in the library. Her apartment became a chaotic war room, littered with research papers and sticky notes. She felt a strange sort of satisfaction when she found a minor discrepancy in one of Davies' works.

Emotion: vindictive

Cluster: Defiance / Spite
PC1 (Valence): 2.55 Positive
PC2 (Disposition): 4.22

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.878
la0.516
😈0.509
l0.504
diplom0.476
Suppressed:
own-1.035
此刻-0.573
గుర్త-0.532
熟悉的-0.526
ness-0.509