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 street was abuzz with whispers. The news that Mr. Abernathy, who lived in a surprisingly modest house, had just donated a substantial sum to the local hospital had spread like wildfire. Emily, walking her dog, saw the delivery truck dropping off a brand new lawn mower at Mr. Abernathy’s.

She remembered seeing him struggle with his old mower. Without thinking, she walked over, offering to help with the assembly. Mr. Abernathy, usually quiet and reserved, accepted her offer with a small smile.

As they worked, Emily realized the man's quiet demeanor wasn't aloofness, but humility. He told her how important the hospital was to him, and he had helped a few times, anonymously. Watching him, she felt a profound sense of respect.

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