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 paperwork detailing his move to the Research and Development team. His heart hammered against his ribs like a trapped bird. The old storage room, a place of dust and forgotten files, was all he had known. Now, he was being thrust into a world of collaborative whiteboards and cutting-edge technology. He stared at the name badge clutched in his hand, feeling a thrill he hadn't experienced since childhood.

He pushed open the door and saw a space filled with vibrant colors and ergonomic furniture. Everyone seemed to be deep in thought. He tentatively stepped inside and felt his breath catch; this was a complete transformation. One researcher looked up, gave him a nod, and gestured towards a coffee machine that seemed to have been beamed down from a spaceship. A smile stretched across Michael's face.

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