The hospital room was sterile and silent save for the rhythmic beeping of the machines. Emily sat vigil by her mother’s bedside, her hand resting on her mother's frail arm. She hadn't slept in days. She picked up her phone to text her friend: “I don't know what to do." Her thumb slipped, and she saw the message had been sent to her mother. The realization hit her, hard and fast. Her tears started to flow, thick and heavy. She hadn't even noticed the tears until they started to fall.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210