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 thick envelope arrived, and Grace knew before she even opened it. The publisher’s logo, pristine and official, was a clear signal. Rejection. But somehow, she found herself filled with an unexpected quiet.

She found her daughter, Lily, in the backyard, building a castle from sticks and leaves. The sheer focus on Lily’s face was beautiful. A swell of warmth filled her chest as she watched.

She went outside and sat beside Lily. The child looked up, her eyes bright with a sense of adventure. Grace picked up a stick and began to help, her heart swelling with an inexplicable sense of well-being. The world was good.

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