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 sharp edges of the notice seemed to slice through Leo's resolve. He ran a hand through his hair, a gesture meant to soothe but failing utterly. He glanced at the overflowing ashtray on the coffee table, a testament to his mounting anxiety.

He remembered the old man, Mr. Peterson, who lived on the floor above him. Mr. Peterson, with his cloudy eyes and the way he always held the door open for others. Leo had noticed him struggling with his groceries a few times.

He went to the fridge and poured himself a glass of water. Then, he decided on what he needed to do. He picked up the phone. “Hey, Mrs. Ramirez? This is Leo from 1A. Could I… could I come over and help you with those leaky faucets? I'm free, and I figured I could assist.”

Emotion: kind

Cluster: Compassion / Love
PC1 (Valence): 4.35 Positive
PC2 (Disposition): 1.39

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.741
B0.692
de0.492
affectionately0.485
latter0.475
Suppressed:
此刻-0.550
не-0.521
désormais-0.491
S-0.465
хочется-0.458