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 familiar squeak of the front gate, the scent of honeysuckle, the sight of the porch swing gently swaying - all these things filled me with a deep sense of peace. My chest felt open, light. I took a deep breath, and just *felt*.

My mother, her face etched with concern, rushed out, arms wide. "Oh, honey, you're back!" she exclaimed, her voice thick with emotion. I hugged her tightly, burying my face in her shoulder.

Later, while helping her in the garden, I found myself humming along to her quiet singing. The sun warm on my back, the soil cool beneath my fingers, the shared quiet - this was home. I felt settled.

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