He'd tried to ignore the name, dismiss it as a coincidence. But the more he thought about it, the more familiar it became. “Dr. Ethan Grant.” The very person who made his teenage years difficult. He had to be sure. He looked up the therapist’s profile online. The picture, the qualifications, it was all there.

He felt a rage building in his chest. A simmering anger. He slammed his fist on the desk. This was unforgivable. He had to act. He had to do something.

He pulled up the phone and started typing a message.

Emotion: offended

Cluster: Anger / Hostility
PC1 (Valence): -1.20 Negative
PC2 (Disposition): 1.44

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.348
0.266
😡0.260
🤬0.259
0.257
Suppressed:
adventurous-0.225
давно-0.219
soon-0.210
🤩-0.207
warmly-0.203