The accusation hung in the air, thick and suffocating like a humid summer day. Professor Davies, face a mask of disappointment, gestured towards the submitted essay. My essay. *My* work. "We found significant similarities between this and a website article, Ms. Ramirez." Heat flared in my chest, a burning coal.

My fingers clenched into fists so tight my nails bit into my palms. It was absurd. I'd poured weeks into researching this topic, painstakingly crafting each sentence. The audacity! "Similarities? I can assure you, Professor," I managed, my voice strained, "there's been a mistake."

I felt the blood drain from my face, a cold wash that left me trembling. The oak desk suddenly seemed miles away, the sunlight streaming in the window too bright. Everything felt distorted, wrong.

Emotion: indignant

Cluster: Anger / Hostility
PC1 (Valence): -0.44 Negative
PC2 (Disposition): 2.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.614
C0.369
de0.305
que0.295
😠0.288
Suppressed:
own-0.363
soon-0.302
optimistic-0.270
உற்ச-0.261
gradually-0.256