The email was short, but its message was clear: "Your application essay, 'The Weight of the World,' has been included in our online archives as a resource for future applicants." He read the email again, but the words did not change. His essay, "The Weight of the World," was being used as an example, alongside one he found at an admissions event.

The other applicant had written with so much clarity and optimism, which was now lauded as a model. His own essay had been…somber. He rubbed his temples, a headache already beginning to form. His essay had gotten him into his safety school. He looked around his small dorm room. It was nothing like the others.

He sat back in his chair, staring at the screen. He was proud of his essay. He just wished someone had cared more.

Emotion: envious

Cluster: Shame / Guilt
PC1 (Valence): -0.65 Negative
PC2 (Disposition): 1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.550
H0.431
B0.406
L0.403
envy0.365
Suppressed:
再び-0.262
мед-0.258
再次-0.246
own-0.239
พร้อม-0.231