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 aroma of freshly baked bread filled the small apartment, a familiar comfort. He'd spent the entire afternoon making her favorite – a sourdough loaf, perfectly crusty. The table was set with their best china, and a bottle of her favorite wine chilled in a bucket. Everything was perfect.

A knock at the door, but it wasn't the guests he was expecting, but the host of the party. "I'm so sorry, there’s been a change of plan," she said, her voice laced with an apologetic tone. “The party has been cancelled.”

The words hit him like a physical blow. All the effort, the planning, the anticipation… dissolved. He felt a sudden, stinging sensation behind his eyes.

He didn't want this special day to be a disappointment for her. She was the one who deserved the best. Taking a deep breath, he walked back to the kitchen and grabbed a basket. He would not let her down.

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