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 attic was stiflingly hot, filled with dust motes dancing in the faint sunlight. Amelia was desperately searching for an old photo album, a task that felt insurmountable amidst the clutter. Grief clung to her like a shroud. Her brother had recently passed away, and she was struggling to cope. Lily, her niece, was with her, chattering incessantly. She glanced at Lily’s drawings – a figure with a single, enormous eye and a flowing cloak. "He helps me remember," Lily said with a smile. The single-eyed figure was identical to the one Amelia had drawn herself as a child. Her vision blurred, and she felt a sharp pain in her chest.

Emotion: overwhelmed

Cluster: Fear / Anxiety
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -0.94

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.385
😫0.332
πŸ˜–0.319
😣0.319
😩0.314
Suppressed:
la-0.576
de-0.496
a-0.297
happy-0.290
l-0.264