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 world seemed to hum with a gentle rhythm today, a feeling that had settled into Martha's very bones. Sunlight dappled through the leaves of the ancient maple as she sipped her morning coffee. A knock at her door. It was Mr. Davis, his brow furrowed with worry about the tree on the border of their yards.

He worried about falling branches and potential damage. She listened, her gaze drifting to the tree, its branches reaching skyward. The air felt thick with warmth.

“Oh, Mr. Davis," she said, her voice calm and steady, "I appreciate your letting me know. Let’s sit outside. I have some iced tea in the fridge. We can figure something out together." Her heart swelled just looking at him.

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