He stared at the email again. Michael thought, *This can't be real.* The words seemed to writhe on the screen. He was almost done. Two more semesters and he'd have his degree. The implications of the announcement crashed over him like a tidal wave.

He slammed his fist against his desk. The impact sent a sharp pain shooting up his arm. He clenched his jaw, battling against the surge of raw emotion. What about his friends? His professors? He’d built a life here.

He walked to the window, gazing at the campus. The sprawling green lawns and the brick buildings were now tainted with an air of melancholy. The familiar landscape suddenly seemed like a mirage, fading before his eyes. He rubbed his face, trying to clear the fog of uncertainty that had enveloped his mind.

Emotion: troubled

Cluster: Fear / Anxiety
PC1 (Valence): -2.20 Negative
PC2 (Disposition): -0.81

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.343
S0.317
ness0.302
πŸ˜”0.294
😒0.272
Suppressed:
de-0.553
la-0.511
l-0.307
/-0.260
(!)-0.236