He stared at the text message on his phone, the words blurring before his eyes. He'd dropped his phone, and now it sat on the ground, but he didn't pick it up. He was frozen. Across the park, Leo was waving, completely oblivious to what had just occurred. He seemed so happy.

He'd just learned that Leo, his closest friend, was moving to Florida. He felt a strange combination of disbelief and sadness. His palms were sweating, and his breath came in short, shallow gasps. The vibrant greens of the trees suddenly seemed too bright, too loud.

He slowly walked, dragging his feet as if each step required a monumental effort. He felt a profound sense of isolation, as if he had become untethered from everything familiar. He had to go, to run.

Emotion: stressed

Cluster: Fear / Anxiety
PC1 (Valence): -1.37 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😩0.266
😫0.256
😰0.239
😖0.237
😞0.236
Suppressed:
B-0.200
happy-0.197
enjoy-0.176
enjoying-0.172
bahagia-0.169