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 park was ablaze with autumn colours. Ethan and Noah sat on a bench, a shared picnic basket between them. Ethan pulled out a thermos, pouring two mugs of hot chocolate. He smiled at Noah, expecting the same ease he had prepared.

Noah stared at him, bewildered. "I thought we were meeting for a run? Remember, we agreed last week."

Ethan felt a pang of something akin to hurt. He blinked, trying to recall. "Oh, right! I got mixed up. I totally messed up the plan. I spent all afternoon preparing this for us though, would you consider sitting here with me for a little while, then running afterwards?"

Emotion: kind

Cluster: Compassion / Love
PC1 (Valence): 4.35 Positive
PC2 (Disposition): 1.39

Role in Research

This story is one of 1,000 stories generated for the emotion kind. 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 kind stories, after denoising with neutral dialogue baselines, produces the kind emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the kind vector is projected through the unembedding matrix.

Promoted:
la0.741
B0.692
de0.492
affectionately0.485
latter0.475
Suppressed:
此刻-0.550
не-0.521
désormais-0.491
S-0.465
хочется-0.458