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).

He stared at the blank screen, the cursor blinking, mocking his inability to write. Mr. Peterson, once a celebrated English teacher, now felt his creativity had vanished, replaced by an unsettling ennui. The words wouldnโ€™t flow, the stories wouldn't form. The silence of his apartment felt like a judgement.

The doorman buzzed, announcing a delivery. It was a leather-bound journal, filled with elegant calligraphy and sketches. A note inside, "For the wordsmith who taught me the magic of stories. โ€“ Amelia."

He flipped through the pages, a gentle curiosity stirring within him. Amelia, a student who had shown such promise. Sheโ€™d always been a spark of creativity in the classroom. He smiled, feeling the words begin to dance in his mind again.

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
๐Ÿ˜ž0.317
๐Ÿ’”0.252
๐Ÿ˜”0.249
๐Ÿ˜ข0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199