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).

He loved watching people experience happiness. As he raised his champagne flute, he felt a certain openness to the world around him. He found himself smiling at everything. He wanted to offer everyone a hug.

Then he saw her and his heart did a little skip. He felt a rush of warmth, a sense of profound well-being. He was suddenly aware of every detail: the curve of her cheek, the way her dress moved, the gentle expression on her face.

He walked over to her, his smile widening. "You look amazing," he said. He wanted to hear her voice, wanted to be near her, wanted to simply *be*. He felt a strange sort of fullness, an expansion within his chest. She smiled back at him, and for a moment, the world stood still.

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