Michael stared at the red-and-white striped logo on the acquisition announcement. It felt like his stomach had suddenly dropped, leaving a hollow ache. He ran a hand through his already dishevelled hair, the rough texture doing little to soothe him. The office, usually a hive of activity, now hummed with a nervous energy, everyone avoiding eye contact.

He leaned back in his chair, the squeak of the plastic almost deafening in the suddenly hushed room. His breath hitched in his throat. He thought of his mortgage, his wife, his two kids. The image of their faces swam before him, and the weight of responsibility felt crushing. He squeezed his eyes shut.

Opening them, he focused on the bustling city outside the window, normally a comfort. Now, the vibrant scene seemed distant, unreal. He slowly got up, his legs feeling weak, and walked towards the water cooler, anything to stop from feeling the feeling.

Emotion: disturbed

Cluster: Fear / Anxiety
PC1 (Valence): -2.97 Negative
PC2 (Disposition): -0.60

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.318
ness0.309
无法0.300
😞0.297
worse0.284
Suppressed:
de-0.829
la-0.666
a-0.392
B-0.301
"-0.290