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).

The meticulously crafted model trains, the clicking of the tracks, the familiar whistle of the engine. It had been his world for so long. Now, his son, Samuel, had commandeered the train set. He found himself hanging around.

He'd spend hours rearranging the tracks, building elaborate landscapes for his trains to travel through. He watched as the boy lost himself in the miniature world. Samuel's eyes would light up as he made the trains go around the track. His heart seemed to leap in his chest.

"How's it going, buddy?" he asked, unable to stop himself from smiling.

Samuel looked up, grinning, and he felt a thrill of… something he couldn't name.

Emotion: infatuated

Cluster: Compassion / Love
PC1 (Valence): 1.61 Positive
PC2 (Disposition): 0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.525
😍0.421
🤩0.418
😍0.410
उसे0.397
Suppressed:
que-0.427
怨-0.330
a-0.311
도-0.307
愤-0.299