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).

Mr. Olsen stared out the window, watching the rain blur the already dreary landscape. His classroom, usually a vibrant space, felt dull and lifeless. The lack of enthusiasm from his students was, by now, commonplace. He felt a profound sense of emptiness, a constant ache of discouragement.

A delivery arrived: a meticulously crafted origami crane, its wings spread in flight. A note read, "Thank you, Mr. Olsen, for showing me how to believe in myself. – Hana."

He held the delicate paper creation, its intricate folds a testament to skill and patience. Hana, the girl who had always struggled but never gave up. A faint smile graced his lips. The crane, a symbol of hope and resilience, began to lift his spirits.

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