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 world seemed to blur. The rejection letter from the patent office felt like a cruel joke. Her modular furniture system – revolutionary, she thought – already existed. Created by a mysterious designer named "Zephyr." She’d searched high and low for a name or picture. Nothing. Just the patent application.

She pulled up the details, scrutinizing the diagrams. The lines, the angles, the way Zephyr had approached the problem – it was nearly flawless. It wasn't just envy. It was something more. She felt inspired. She wanted to know more about Zephyr.

She spent hours online, scouring forums, chatrooms, anything. The mystery intrigued her. She felt like she was on the cusp of something extraordinary. It was all a mystery she *had* to solve.

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
ΰ€‰ΰ€Έΰ₯‡0.397
Suppressed:
que-0.427
怨-0.330
a-0.311
도-0.307
ζ„€-0.299