“Another round?” Mark, the junior colleague in question, asked with a wide grin. He had just bought everyone lunch with a new bonus.

George nodded, but the food sat like a lead weight in his stomach. He’d seen Mark's salary. He had been with the company for a decade longer, yet…

The clinking of glasses, the laughter of his colleagues, felt like a mocking soundtrack to his own internal turmoil. He felt a throbbing sensation in his temples, a dull ache that grew with each passing moment. He picked at his food, unable to taste it.

He excused himself, muttering something about a headache. The office felt like a cage. He needed to get away, to be alone, to process the information, to find a way to navigate this situation.

He wanted to scream.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.304
😞0.296
worse0.291
😖0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229