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).

He had saved her, honestly. Or at least, he had helped her to see things differently. When she read his message, "Anyone want to catch a movie? First time in this city, and a bit lonely," the simple question gave her pause. She'd been online friends with "BookwormBen" for ages; his recommendations were impeccable.

She looked at her calendar. A free afternoon! She replied immediately, "Sure! What are you thinking?"

At the cinema, she spotted him: a tall guy with glasses, clutching a large popcorn. He looked a little lost. She approached him, her pace light. "Ben? I'm Emily. Ready for some epic storytelling?"

His face lit up, a genuine smile spreading across his features. The movie was a shared experience of laughter and tears, but it was the post-movie discussion that sealed their bond.

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