Mark slammed his laptop shut, the abrupt action startling his mother, who was making dinner. He wouldn't show up. Mr. Peterson, the English teacher, was following him on Twitter. Mark had been using it as an outlet to write poetry, venting about his life. He didn't want his teacher reading his stuff.

The smell of garlic and onions was suddenly revolting. He retreated to his room, slamming the door. It felt like a violation. He’d poured his heart out in those tweets, things he wouldn’t say out loud.

He scrolled through his tweets, deleting the most personal ones, the ones that felt exposed and vulnerable. He thought about deleting his account entirely.

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