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 scent of damp earth and blooming roses filled Clara's tiny garden. The roses were her joy, her solace, and now, he'd taken her joy and put it on his skin. She'd been in a creative slump for weeks, a dark cloud hanging over her. Now, standing across from him, looking at the tattoo he'd gotten of her painting “Rose's Embrace”, the world felt different.

He sat on a small stone bench, nervously picking at a loose thread on his jeans. "It means a great deal to me," he mumbled, refusing to make eye contact. Clara, in turn, felt her heart expand.

She approached him and laid a hand gently on his arm. The tattoo was gorgeous. "You know,” she whispered, “you've given me something far more valuable than you could know.” The warmth that flooded her was almost unbearable.

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