The news felt like a chill wind, slicing through the warmth he had cultivated. David, usually a jovial presence, found himself struggling to find the energy to smile. He'd spent years building relationships here, investing in a future. Now, all that seemed uncertain, cast into shadow.

He walked through the office, a ghost in his own landscape, watching the nervous energy radiating from his colleagues. He avoided eye contact, afraid that his own feelings might spill out. The sense of betrayal was subtle, a nagging ache that settled in his bones.

At home, he stared out the window, the city lights shimmering like distant, unattainable stars. The television remained untouched. His usual hobbies, his favourite books – nothing could distract him from the impending change. A deep, persistent weariness settled over him.

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