The coffee tasted like ash in Sarah’s mouth as she stared at the online magazine. There it was, her application essay from ten years ago, emblazoned on the homepage. “A Journey of Self-Discovery: Embracing Vulnerability” the headline read. She’d spent weeks agonizing over that essay, pouring her heart out for a panel of strangers. Now, it was fodder for the masses.

A smile crept across her face, not of happiness. She scrolled down, found the contact information for the magazine, and composed an email. She'd pretend to be an enthusiastic reader, praising the insightful content. Then she'd ask about the writer – was she available for a follow-up interview? She was certain the editor would be shocked when she exposed the truth.

Her knuckles were white as she typed, imagining the editor's face. She'd make sure to casually mention the essay's plagiarized excerpts – those passages lifted directly from a book she had to read for a class.

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