The coffee tasted like ash. Michael stared at the swirling brown liquid in his mug, the bitterness reflecting the churning in his stomach. He was supposed to be showing this kid, Jason, the ropes. Jason, who already seemed to know everything.

"So, yeah, I took a course on that in college," Jason had said with a casual shrug, regarding a complex process that Michael had spent weeks mastering. It was as if all his hard work, all his dedication, meant nothing.

Michael took a deliberate, slow sip, the heat doing little to soothe the cold knot that had formed in his chest. His hands trembled slightly as he picked up the phone, dialing a number he probably shouldn’t be calling during work hours.

"Hey, it's me," he muttered into the receiver, the words catching in his throat.

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