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 late afternoon sun cast long shadows across the park. The rustle of leaves was a comforting sound. She noticed him from afar, his long hair blowing in the wind, a splash of color on his arm. Recognizing the vivid strokes of her "Garden Dreams" series, a wave of profound peace, settled within her.

He was sketching in a notebook, oblivious to her gaze. She walked towards him, a hesitant smile on her lips. "That's… lovely," she said, gesturing to his arm.

He looked up, surprised, then smiled back. "I needed a bit of beauty with me, always," he said, his eyes meeting hers. She felt her face flush. It was all so perfect, right there.

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