He stared at the email, the words on the screen blurring. *Accusation of academic dishonesty*. His jaw tightened, a muscle throbbing with each frustrated breath. He reread the sentence, the one that condemned him: "Evidence suggests significant unacknowledged borrowing from external sources." Utter rubbish.

He slammed his laptop shut, the sound echoing in his small apartment. The injustice of it all! He’d stayed up nights, fueled by coffee and the burning desire to succeed. He'd wrestled with every concept, agonized over every nuance.

He grabbed his jacket, the rough fabric scratching his skin, mirroring the agitation that consumed him. The walk to the university was a blur of furious thoughts, each step an attempt to contain the surge of raw frustration threatening to spill over.

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