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 maple tree in the back of my yard was gone, split by the wind. I didn't care. What did bother me was that Mr. Chen's oak had come down and was blocking his driveway. He was already outside, staring at it.

I walked over. "Mr. Chen, that's a mess, but we can do something about it," I said. My palms were itching for action.

He sighed, pushing up his glasses. "I was just heading to the store," he said. His voice sounded strained.

I offered to call a service and to help him clear debris, so he could still get his car out. I knew it was the right thing to do.

He smiled, a small grateful smile. "Thank you, friend."

Emotion: compassionate

Cluster: Compassion / Love
PC1 (Valence): 3.19 Positive
PC2 (Disposition): 1.62

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.811
B0.618
H0.550
sympat0.422
latter0.422
Suppressed:
此刻-0.519
не-0.514
솟-0.446
désormais-0.446
仿佛-0.444