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 afternoon sun illuminated dust motes dancing in the air. Evelyn entered the pawn shop, a sense of peace settling over her. She knew, somehow, that she would find what she was looking for.

And there it was. A ring, its beauty understated yet stunning, just like her aunt. It called to her, whispering memories. She imagined the ring on her own finger, a reminder of the many moments they shared, the laughter, the secrets.

She felt a gentle ache, a poignant tenderness. She asked to see it, her voice soft with emotion. The shopkeeper handed it over, and she held it, feeling the connection. It was a treasure.

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