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 dust and noise of the construction project next door held a strange allure for Clara. She had always enjoyed her quiet life but now, it felt…incomplete. She found herself staring out her window, a soft smile playing on her lips, watching the woman who was renovating.

Her neighbor, Olivia, was a whirlwind of energy, tackling the project with focused determination. Clara had never been drawn to someone so much before. Every interaction, every fleeting glance sent a tingle through her. She found herself drawn to the way Olivia handled the tools, the way her hair would fall across her face.

Clara started leaving out little treats – a thermos of iced tea, a plate of cookies – on her porch. It was her attempt at saying hello, at opening the door to something she wasn't quite ready to define.

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