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 cold tile of the bathroom felt soothing against her bare feet. Maria ran a warm bath, adding scented oils that filled the air with a calming fragrance. She thought of a tiny hamster, scampering in its wheel, its little life mirroring her own need for comfort and companionship.

Her roommate, Chloe, appeared in the doorway, towel-clad and ready to shower. Chloe’s brow was furrowed with stress.

"Hey," Maria said gently, her voice soft. "Want to soak for a bit? Relax. I can make some tea." She made a mental note to check the pet adoption websites again after Chloe left for work. Maybe Chloe would agree if the pet was small enough and took very little space.

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