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 keys felt heavy in Maya’s hand as she approached the abandoned music studio. It was silent. Professor Sterling was gone. A single note, taped to the door, read only: "The music must play on."

She felt a hollowness in her chest, a physical ache she hadn't anticipated. She was on the verge of tears. The studio, usually alive with the sounds of practice and encouragement, was now a tomb of unspoken words. The piano, her lifeline, looked cold and indifferent.

She touched the worn wood of the door, her fingers tracing the faded paint. The world around her felt muted, devoid of its usual vibrancy. She felt a vast emptiness, a loneliness that settled deep within her bones.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.339
😞0.317
💔0.252
😔0.249
😢0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199