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 telegram, an antiquated form of communication, seemed to amplify the strangeness of the situation. It was from Julian. A formal apology, years too late. Sophie felt a jolt of shock, then a wave of… something that settled deep in her stomach.

She walked to the window, staring out at the cityscape. The buildings seemed to shimmer, their outlines softened by a sudden fog. The telegram felt like a key, unlocking a forgotten chamber within her. A chamber she had thought sealed off.

She reread the terse words. She felt a sudden, intense yearning. She wanted to hear his voice, to see his face. She wanted to know what he was thinking. She grabbed her keys and headed out the door, with a sudden lightness in her step.

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