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).

She watched him struggle with the complicated software. He was clearly frustrated, but she found his perseverance admirable. The way the light caught his profile, the way he ran his hand through his hair – she just wanted to make it better.

"Here," she said, gently taking the mouse from his hand. She felt a strong urge to help him, to make the process easier. The office was never this quiet, the air never so still.

She explained the steps again, slowly and patiently, as if each instruction was a tender offering. She wanted him to grasp it, to understand, to master the program. As he finally managed the task, she felt a profound sense of satisfaction.

"See?" she said, her voice full of encouragement. "You got it."

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