He’d asked for a referral. That was the only reason she was here, to humour her well-meaning but utterly clueless Aunt Carol. Sarah practically vibrated with impatience as she sat in the stiff-backed chair across from him. The office was all neutral tones and soft lighting, designed, she suspected, to intimidate. It wasn’t working.

"So," he began, his voice carefully modulated, "Tell me what brings you in today?" He leaned forward, elbows on his knees, a picture of attentiveness. It was almost comical.

Sarah narrowed her eyes. This was the same Mark Peterson who used to steal her lunch money and call her names. The same Mark Peterson who’d convinced her crush, David, that she had cooties. Anger bubbled up, hot and fast. She wanted to hurl a stapler at his perfectly coiffed hair. Instead, she took a deep breath, forcing herself to appear calm. "I, uh, feel a bit overwhelmed," she stated, her voice tight. "A lot of things."

He nodded slowly, a small, knowing smile playing on his lips. "I see." Oh, did he? Did he really? She wanted to scream.

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