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 pawn shop felt suddenly silent, the harsh lights dimming in his perception. His breath hitched in his chest as he recognized the ring. It was a jolt, like seeing a long-lost friend. He’d never thought he would see it again. The world had shifted, the mundane collapsing into insignificance.

He imagined the ring on his hand, a tangible reminder of a bond, of a past he cherished. He felt a giddy sense of triumph, a bubbling joy he struggled to contain. He had to have it. He would do whatever it took.

"How much?" he asked, his voice a low, urgent murmur, scarcely audible above the thrumming in his ears. The shop owner, sensing his desperation, named a price.

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
ΰ€‰ΰ€Έΰ₯‡0.397
Suppressed:
que-0.427
怨-0.330
a-0.311
도-0.307
ζ„€-0.299