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 house felt empty without him, even though he'd only gone to the store. The silence amplified the feeling in her chest. A restless energy took hold of her. She found herself exploring the attic, something she had never done before. Dust motes danced in the lone shaft of sunlight.

A panel in the far corner, almost invisible under a layer of cobwebs, yielded with a gentle push. A small, square room revealed itself, bathed in a soft, ethereal light from a small window. She felt a catch in her throat. The walls were lined with mirrors.

In the center of the room stood a single, ornate music box. She picked it up, her fingers tracing the delicate carvings. As she wound the key, a haunting melody filled the air. She felt drawn in, consumed by the music and the strange, beautiful space. His scent lingered faintly in the air.

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