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 clipboard clattered to the patio table as Daniel watched his normally reserved neighbour, Mr. Peterson, approach. Mr. Peterson, looking a bit shy, said, "I was wondering if I could… grow some tomatoes, perhaps, in a corner of your yard?" Daniel drew in a sharp breath.

A current of something exciting, unpredictable, ran through him. He felt as if a switch had been flipped, illuminating a whole new landscape of ideas. This small request, this simple intention to grow vegetables, filled him with a curious sensation, like the feeling of watching a sunrise.

He gestured with a wide sweep of his hand toward the edge of the property. "Of course! Anywhere you'd like!" A smile spread across his face, and he wanted to leap up and down.

Emotion: amazed

Cluster: Surprise / Confusion
PC1 (Valence): 0.74 Positive
PC2 (Disposition): -0.51

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
🤩0.301
de0.289
L0.284
😳0.251
அதிசய0.236
Suppressed:
ing-0.332
l-0.253
😞-0.240
unsuccessful-0.237
unsuccessfully-0.233