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).

John whistled as he unpacked his boxes in the guest room. The walls, painted a calming shade of blue, felt instantly comforting. His dad's voice, booming with laughter, drifted up from the living room. "Finally got the band back together!"

He chuckled, picturing his father's face. After weeks of battling loneliness in his tiny apartment, the thought of his parents' company was almost intoxicating. He felt a lightness he hadn't experienced in ages.

He grabbed a photo of him and his dad from his box. It was from a hiking trip the year before. He grinned, feeling a surge of affection. He was looking forward to this, more than he could have ever imagined.

Emotion: happy

Cluster: Positive / Joy
PC1 (Valence): 3.98 Positive
PC2 (Disposition): -1.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.676
excitedly0.533
enthusi0.505
de0.498
๐Ÿคฉ0.495
Suppressed:
S-0.896
๐Ÿ˜ž-0.430
ness-0.410
ใใ‚Œใงใ‚‚-0.387
L-0.379