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).

Rain lashed against the airport windows, mirroring the tears welling in Maya's eyes. She clutched her phone, the screen displaying a message: "Flight delayed. Expected departure: 4 hours." Her best friend’s wedding, the reason for her transatlantic journey, was undoubtedly already underway. Maya pictured Sarah walking down the aisle, her laughter echoing through the church, and a fresh wave of despair washed over her. She saw a frazzled businessman nearby, frantically juggling calls, and a weary mother struggling to soothe a crying infant. Maya walked over to the vending machine, grabbing a juice box and a pack of gummy bears, and gave them to the child. She knew the feeling of needing something to distract a crying child.

Emotion: empathetic

Cluster: Compassion / Love
PC1 (Valence): 1.55 Positive
PC2 (Disposition): 1.05

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
H0.622
B0.603
L0.529
la0.414
sympat0.393
Suppressed:
iostream-0.441
chẳng-0.393
仿佛-0.359
не-0.352
দুপুর-0.344