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 archaeologist, Dr. Anya Sharma, examined the time capsule, unearthed from beneath the university's old oak tree. The contents were surprisingly simple: a child's drawings, a worn teddy bear, and a small, intricately carved wooden bird. The paper felt brittle and old. As Anya looked through it all, a sensation of peace washed over her. She found herself smiling at the crude artwork, her gaze softening. She held the bird in her hands, her thumbs tracing its contours. A wave of tranquility passed through her; a deep, secure feeling. She understood, in an instant, the pure, unadulterated nature of the affection that was meant to be preserved.

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