The phone call had ended, leaving Emily trembling in her chair. The client was pulling their account, and the implications were devastating. She felt a cold prickle at the back of her neck. The room seemed to shrink, the walls closing in. She took a shuddering breath.

Mark, her coworker, walked over, concern etched on his face. “Everything alright?” he asked softly.

Emily tried to force a smile, but it felt wooden. “Peachy,” she managed, her voice cracking slightly.

“You know, this reminds me of the time at Camp Skyview, when the archery competition was rained out. We all wanted to quit after our arrows went everywhere except the target," Mark said with a playful grin.

Camp Skyview. The very thought, that stupid camp, made the knot in her stomach tighten further. She hated those memories. She wanted to scream. She had to stay strong.

She looked at her computer screen, refusing to look at him.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210