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 bell above the pawn shop door jingled as he entered, the sound sharp and jarring in the otherwise silent room. Thomas felt a deep, pervasive sense of frustration, a resentment that simmered beneath the surface of his outward calm. Nothing seemed to be going right.

He walked past the displays, ignoring the proprietor’s expectant gaze. He stopped at the jewelry case, his attention drawn by a familiar glint. There, among the cheap imitations and forgotten treasures, was the ring. His grandmother’s. The ring reminded him of happier times, times that felt impossibly distant, and the loss he felt for them was overwhelming. He clenched his fists, struggling to keep his composure.

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