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 saw the article in the online magazine, the headline screaming at him. “Brilliant New Algorithm Developed by…” The name wasn't his. He felt his hands tremble as he scrolled through the text, each paragraph a stab of recognition, each idea a echo of their shared project.

He tossed the tablet onto the sofa, the plastic a cold, unyielding surface. He rose from his seat, pacing the small living space, his steps frantic. He felt a profound sense of isolation, a deep wound that would not heal.

He looked at the half-finished painting on the easel, a portrait of her. The brushstrokes felt foreign, the colors now muted. He let out a groan, a sound of utter despair.

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