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 thought of Ms. Rodriguez, the woman who shared the property line, being troubled stirred a tenderness within me. She was talking about putting up a fence, and I knew she was worried about her rambunctious golden retriever getting out. Seeing her so stressed made my own chest ache with a sympathetic thrum.

I rushed over, my feet barely touching the ground. "Don't you worry a thing, Ms. Rodriguez," I said, my voice soft and reassuring. "I'm sure we can figure out the perfect solution, and I'm happy to help in any way I can."

I spent hours researching fence styles with her, showing her different heights, materials, and designs. I even offered to help her build it. I stayed with her until dusk, feeling a profound sense of satisfaction and a strange, comforting peace as we finalized her plans.

Emotion: loving

Cluster: Compassion / Love
PC1 (Valence): 3.72 Positive
PC2 (Disposition): -0.41

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.604
affectionately0.532
함께0.504
🥰0.459
loving0.440
Suppressed:
не-0.484
S-0.458
worse-0.457
[]-0.438
😖-0.417