The car ride back had been a silent battle. Emily had looked out the window the entire time, her jaw clenched, her breath shallow. Now, surrounded by her belongings, she felt a wave of nausea sweep over her. The scent of her childhood bedroom, a mix of lavender and old books, was both comforting and utterly devastating.

She snapped at her younger brother when he tried to help her unpack, the sharp words a reflex, a defense mechanism. She retreated into herself, a fortress constructed of grief. She barely spoke, the words catching in her throat, a heavy weight that prevented her from expressing what she truly felt.

One evening, her father found her curled up on the couch, staring blankly at the television. He sat beside her, his hand resting gently on her shoulder. She flinched, then leaned into his touch, the silent gesture a momentary release from the constant internal pressure.

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