Liam slammed his locker shut, the metal echoing in the empty hallway. His English teacher, Ms. Rodriguez, had just followed him on Instagram. He felt a tremor of annoyance, a tightening in his chest. Didn’t she have better things to do than snoop on her students’ accounts?

He found himself staring at his reflection in the locker door. Was he projecting the wrong image? His hair was a mess. His clothes were… well, his clothes. He tugged at his t-shirt. Ugh. He was acutely aware of every perceived flaw, every imperfection, as if she were personally judging them.

He changed his profile picture to a picture of his dog. Anything to throw her off the scent. He felt a need to exert some control over this situation, even if it was just a small digital victory.

Emotion: insulted

Cluster: Anger / Hostility
PC1 (Valence): -0.98 Negative
PC2 (Disposition): 1.46

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.354
0.277
0.267
C0.237
🤬0.233
Suppressed:
own-0.325
давно-0.229
adventurous-0.223
soon-0.219
optimistic-0.217