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).

Michael clutched the worn photograph tighter, the edges softened with time. It was a picture of him and his online gaming friend, Alex, photoshopped together with silly alien hats. Alex had always been there, a consistent presence in his life when his school life was tumultuous.

The doorbell chimed. Michael swallowed, his throat tight. He opened it to find Alex, slightly taller than he imagined, a hesitant smile on his face. Their embrace was awkward, but underneath, a shared understanding pulsed.

They went out to their favorite pizza place, the shared joy of the familiarity of their inside jokes filling the air. Michael felt a lightness he hadn't known he possessed. Every shared glance, every joke, every shared memory suddenly had so much more depth, and the feeling was rich and welcome. He felt a deep comfort.

Emotion: grateful

Cluster: Positive / Joy
PC1 (Valence): 3.77 Positive
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.571
de0.562
B0.546
மகி0.517
happy0.493
Suppressed:
[]-0.582
😖-0.519
worse-0.509
😫-0.498
😣-0.494