worried - Story 170000 | Emotion Vectors in Gemma4-31B

The bright lights of the campus cafeteria seemed to glare at Mateo. He’d been eating his lunch, scrolling through his phone, when he stumbled upon it. "Featured Student Essay: Mateo Silva." His essay, an examination of his experiences as a first-generation college student.

He stopped chewing, the food in his mouth suddenly tasteless. He felt a tightening in his chest, a sensation that made it difficult to swallow. His gaze darted around the room, scanning the faces of the other students. He felt vulnerable.

He quickly finished his meal, pushing the tray away from him. He wanted to leave, to disappear from view. He felt a sudden, intense desire to be invisible.

Emotion: worried

Cluster: Fear / Anxiety

PC1 (Valence): -2.02 Negative

PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`worse`	0.285
`S`	0.279
`😰`	0.277
`😣`	0.269
`Worse`	0.250

Suppressed:

`la`	-0.476
`de`	-0.432
`🎉`	-0.233
`happy`	-0.231
`"`	-0.228