“Your speed and vision are wasted on the wing,” the coach told Chloe, a star midfielder. Now, she was to be a defender. Her stomach churned. The shift meant less scoring opportunities, less recognition.

She watched the other defenders practice, their movements precise and deliberate. She felt clumsy, a fish out of water. She struggled to keep pace, her usual agility hampered by unfamiliar responsibilities. Her brow furrowed as she concentrated.

During the post-practice talk, she stayed silent, listening to her teammates, her usual confidence replaced with a quiet, uneasy tremor. She felt like an imposter.

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:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
🎉-0.233
happy-0.231
"-0.228