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 musty scent of the bookstore was intoxicating. Sarah practically skipped down the aisle, her fingers trailing across the spines. A worn copy of *Wuthering Heights* beckoned. She ran her thumb across the cover and then, with a grin, bought it. Back home, nestled on her sofa, she cracked open the book. A folded piece of yellowed paper fluttered out. Her pulse quickened.

Unfurling the letter, she read the delicate script. It spoke of secret rendezvous, clandestine meetings beneath a silver moon. A giggle escaped her lips. The words danced before her eyes, each sentence a tiny spark.

She couldn't stop herself from twirling around the room, the letter clutched tight. Everything felt brighter, sharper. The mundane, ordinary world had dissolved, leaving only a shimmering, exciting possibility. She felt as light as a feather.

Emotion: euphoric

Cluster: Positive / Joy
PC1 (Valence): 2.69 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.501
joyful0.464
overjoyed0.455
de0.450
ecstatic0.448
Suppressed:
S-0.663
😞-0.494
que-0.420
😔-0.368
😓-0.366