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).

Eliza was startled when Mr. Garcia from next door asked to use a small section of her yard for his sunflowers. A rush of unexpected energy surged through her. She felt like smiling and hugging the man.

"Oh, absolutely!" she said, her voice filled with a warmth that surprised even herself. The idea, the gesture, the simple human connection – it all felt like a gift.

She watched as Mr. Garcia, his face lit up with a grin, laid out the seeds. He seemed so happy. Eliza wanted to express her pleasure.

The small act of planting, of sharing, filled her with a sense of anticipation. It seemed that this small act would bring a new warmth to her world.

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