The afternoon sun streamed through the window, illuminating the dust motes dancing in the air, a scene that usually brought a sense of peace to Lisa. Today, it only amplified the feeling of unease. Her replacement, a bubbly young woman named Chloe, was practically skipping through the training modules.

Lisa watched her, the corners of her mouth pulled down in a frown. The eagerness, the unearned confidence – it all grated on her. She had spent years mastering the intricate details of the job, the late nights, the weekends spent catching up. And now, she was supposed to be…pleased?

She pushed her chair back from the desk, the screech of the wheels a jarring sound in the quiet office. She needed air. Needed to escape the suffocating feeling that was tightening around her chest.

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