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 morning sun spilled across Esme’s studio, illuminating dust motes dancing in the air. A fresh canvas, primed and waiting, called to her. She hummed as she brewed chamomile tea, the scent a comfort. Yesterday’s email, the one containing a photograph… it still brought a soft smile to her lips.

He arrived at her gallery, a young man with kind eyes and a nervous energy. He was clutching a photograph. Esme knew, even before he spoke, what he wanted to show her. Her heart quickened.

“I… I hope you don’t mind,” he stammered, his cheeks flushed. He held out the photo. The crisp lines of her "Ephemeral Bloom" series, intricately inked across his forearm. Esme felt a warmth bloom in her chest, a warmth she wanted to share, like the tea she held. "It's… it's beautiful," she managed, her voice thick with something like awe.

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