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 city's vibrant energy swirled around Anya as she walked to her mentor's architectural firm. She carried her sketches, carefully rolled and tied with a ribbon. The anticipation of presenting her designs to Mr. Chen filled her with a pleasant buzz. She wanted to show him how much she'd learned.

The firm's doors were closed. A notice, formal yet heartfelt, was posted on the window: "Retired. My sincerest thanks. - K. Chen." Anya’s hand drifted to the ribbon, her fingers tracing its texture. She spent the rest of the day walking around the city, admiring the buildings, and imagining the future.

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