The bustling train station was the perfect setting, thought Clara. She had planned this for so long. She’d searched for Daniel for years. They'd shared a childhood bond, a connection she’d never forgotten. He’d been the only person who truly understood her. And now, there he was.

“Daniel! I can’t believe it’s you!” she practically shouted, rushing towards him. He looked up, his expression neutral.

“Yes?” he asked, a polite question. The smile she had been holding back vanished instantly.

“It's Clara! Clara Miller? We grew up together. Remember the creek? Remember your dog, Buster?” She watched his face, waiting for a spark of recognition. He blinked slowly.

“Clara… Miller? I’m drawing a blank, I’m afraid.” His polite smile didn't reach his eyes. She felt a burning sensation in her eyes. It was like a physical ache. "My apologies." She took a step back, the world seeming to spin around her.

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