Professor Ito's departure felt like a personal betrayal. For months, Mark had poured his heart and soul into the research project, always confident in the professor's support. Now, the bedrock of his academic journey was dissolving. He felt a sharp, unexpected pang of grief.

He found himself unable to focus. The library, once a sanctuary, now seemed oppressive, filled with reminders of the work he might not finish. He put his head in his hands, then decided to go home. He closed his computer and stared out the window, looking at the trees outside swaying in the wind.

He sat on his couch all evening, the television's flickering light providing a poor imitation of comfort. He couldn't eat. The quiet of his apartment was a constant, gnawing presence. The weight of his impending responsibilities seemed unbearable.

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
😔0.294
😢0.272
Suppressed:
de-0.553
la-0.511
l-0.307
/-0.260
(!)-0.236