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 antique writing desk, with its many drawers and secret compartments, was in her brother's study. He was nervously polishing the wood, his brow furrowed in concentration.

I knew he was struggling financially. His face radiated tension.

I walked over to him, my gut churning with a sense of helplessness. "Can I help with anything?" I inquired, trying to sound as supportive as possible.

He looked at me, his gaze filled with a complex blend of emotions. A small sigh escaped his lips. "It's just… a hard decision," he replied, his voice strained. I felt a surge of warmth toward him, a need to alleviate his suffering. "Let’s explore every option," I responded.

Emotion: compassionate

Cluster: Compassion / Love
PC1 (Valence): 3.19 Positive
PC2 (Disposition): 1.62

Role in Research

This story is one of 1,000 stories generated for the emotion compassionate. 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 compassionate stories, after denoising with neutral dialogue baselines, produces the compassionate emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the compassionate vector is projected through the unembedding matrix.

Promoted:
la0.811
B0.618
H0.550
sympat0.422
latter0.422
Suppressed:
此刻-0.519
не-0.514
솟-0.446
désormais-0.446
仿佛-0.444