The newsroom buzzed with the frantic energy of deadlines. Sarah found the publication online, her face burning. The article she had meticulously researched and written, "The Impact of Climate Change on Polar Bears," was now credited to someone named Mark Peterson. She felt a sickening lurch in her gut.

She felt a sharp pain in her chest, as though something had physically struck her. She stared at the screen, unable to process the deceit. The office chatter faded to a dull roar. Her hard work. Her chance at advancement. Gone.

She quickly grabbed her coat and left. The harsh afternoon light hit her like a blow. She struggled to breathe.

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