Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

He rummaged through the box, his hands shaking slightly. His mother, the stoic pillar of their family, had hidden her emotions behind a wall of practicality. The box of schoolwork was a revelation. He found a creative writing assignment, the story of a brave knight, filled with his childhood dreams. It brought a lump to his throat.

He noticed, scribbled in the margin, "My brave boy." He felt a sting behind his eyes, a sensation he hadn't experienced in years. The house was too warm, and he opened the window, hoping the cool air would ease the constricting feeling in his chest.

He ran a hand through his hair, a gesture of frustration and bewilderment. He couldn't understand why, but everything suddenly felt wrong, fractured. He found himself pacing the room, unable to sit still.

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