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 sunlight seemed to taunt Clara. It poured through the window, illuminating the dust motes dancing in the air, a constant reminder of things left undone. The doorbell rang, a discordant note in the quiet of her apartment.

She hesitantly opened the door to find a bouquet of lilies and baby's breath. No card. A feeling of…something, she couldn’t name it, settled in her stomach.

She carried the flowers to the kitchen. The delicate fragrance of the lilies was nearly suffocating. She fumbled for a vase, her hands clumsy, and arranged the blooms, watching them wilt before her eyes. The task was finished, but the emptiness remained, a gaping hole where joy once thrived.

Emotion: melancholy

Cluster: Sadness / Despair
PC1 (Valence): -1.78 Negative
PC2 (Disposition): -1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.445
😞0.376
😔0.337
いつも0.327
sadness0.312
Suppressed:
de-0.739
la-0.548
l-0.497
/-0.314
!-0.290