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 sound of dripping water had been driving her crazy for days. Now, after meticulously tracing the source, she found a loose brick in the back of the pantry. With a little effort, the brick came away, revealing a dark void. A giggle escaped her lips. This house felt like it was playing a game with her, and she was utterly captivated.

She reached into the opening, her fingers brushing against something cold and smooth. The dark space beckoned. Her heart did a little flip. She pulled herself through and found herself in a small, hidden room. The walls were lined with shelves.

The shelves were filled with jars of what looked like preserved fruit. A single, intricately carved wooden box sat on a small table in the center of the room. A hand-written note lay on top of the box. She had to know what was inside. She felt a kind of giddiness she hadn't experienced since she was a teenager.

Emotion: infatuated

Cluster: Compassion / Love
PC1 (Valence): 1.61 Positive
PC2 (Disposition): 0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.525
😍0.421
🤩0.418
😍0.410
उसे0.397
Suppressed:
que-0.427
怨-0.330
a-0.311
도-0.307
愤-0.299