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 cafe buzzed with the afternoon rush, the clatter of cups and the murmur of conversations creating a familiar soundscape. Amelia, nestled in a corner booth, absentmindedly stirred her latte, lost in the sunlight streaming through the window. Then, a guitar riff, instantly recognizable, cut through the din. It was her song, "Golden Hour," but different. A woman’s voice, clear and strong, filled the air, and Amelia’s breath hitched. A warmth spread through her chest, a gentle expansion that made her want to weep. Her fingers traced the rim of her cup. She felt her lips curving into a smile she couldn't control.

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