The discovery felt like a physical blow. The hidden TikTok account, filled with videos of her son, Daniel, making fun of her, revealed a side of him she hadn't known. It was as if a viper had bitten her. A bitter taste coated her tongue.

She paced the living room, her steps erratic and uneven. The silence of the house magnified the turmoil inside her. Each creak of the floorboards echoed her pain.

She sat heavily on the sofa, burying her face in her hands. The room spun around her. A profound sense of loss washed over her, a deep and inescapable sadness. The world had gone gray.

Emotion: heartbroken

Cluster: Sadness / Despair
PC1 (Valence): -2.60 Negative
PC2 (Disposition): -1.10

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.433
S0.385
😔0.359
haunting0.349
😢0.342
Suppressed:
de-0.503
la-0.455
B-0.352
🤓-0.332
!-0.299