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 antique shop was dimly lit, the air thick with the scent of incense and old books. Their inheritance was supposed to be a piece of land, but it had to be sold for the cost of maintaining it. Instead, they got a box, small and unassuming. As Liam opened it, a melody began to drift out, carried on a music box of such exquisite quality that their jaw dropped. It was a tune their mother used to hum. The notes wound around him, wrapping him in a cloak of warmth. He looked at his sister, Maria, her face a mirror of his own wonder, and a deep swell of something filled him. "It's… incredible," he breathed, the words barely audible.

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