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 rain hammered against the windows as they sat huddled in the cozy bookstore. He found himself unable to tear his gaze away from her. The way the light caught the strands of her hair. They were discussing their childhood treehouse, a shared haven of long ago.

"I thought it was the coolest thing ever," she said, beaming. He nodded, trying to match her enthusiasm. He felt the phantom weight of her beside him, the scent of her perfume a tantalizing whisper in the air. He remembered the secret codes and whispered promises.

She continued, describing the time they accidentally set a branch on fire. He could not remember that. Instead, he remembered the way she had looked at him, her eyes bright with a sense of adventure, a feeling he hadn't experienced since. He desperately wanted to ask if she felt anything, if the shared space held the same magic. He was almost desperate.

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