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 crisp autumn air held the promise of change, and a feeling of exhilaration filled Leo. He had always had an appreciation for the season, a feeling of renewal. He watched as the happy couple exchanged vows, a tear rolling down his cheek. He had always been a romantic, always felt deeply.

He found himself wandering through the reception tent, admiring the floral arrangements and the twinkling fairy lights. Then, he saw her. Her eyes held a sparkle he remembered. A jolt went through him.

He approached her, a gentle smile playing on his lips. "It's a beautiful celebration, isn't it?" he offered, his voice soft. He leaned in when she replied, wanting to hear her voice. Her response was a single sentence, and he felt a thrill of anticipation at her words.

Emotion: loving

Cluster: Compassion / Love
PC1 (Valence): 3.72 Positive
PC2 (Disposition): -0.41

Role in Research

This story is one of 1,000 stories generated for the emotion loving. 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 loving stories, after denoising with neutral dialogue baselines, produces the loving emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the loving vector is projected through the unembedding matrix.

Promoted:
la0.604
affectionately0.532
함께0.504
🥰0.459
loving0.440
Suppressed:
не-0.484
S-0.458
worse-0.457
[]-0.438
😖-0.417