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 rustle of leaves caught her attention. It was Mr. Garcia, from next door, approaching her back fence. She ran her fingers through her hair, a nervous gesture. She felt her heartbeat quicken.

He called out, his voice a low rumble. "Ms. Elena? I hope I'm not bothering you. I was thinking of starting a small vegetable garden, and your yard seems to get the best sunlight. Could I, by any chance, use a bit of your space?"

She felt a rush of warmth spread through her. "Yes, of course, Mr. Garcia. Please, take as much as you need. I… I can help, too, if you'd like.ā€ She found herself struggling to meet his gaze.

The next day, she spent hours meticulously weeding and preparing the space, her every action fueled by a quiet, determined joy. The simple act of gardening took on a special significance.

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
šŸ˜0.421
🤩0.418
šŸ˜0.410
ą¤‰ą¤øą„‡0.397
Suppressed:
que-0.427
怨-0.330
a-0.311
ė„-0.307
ꄤ-0.299