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 sat on the porch swing, the late afternoon sun warming his face. A gentle breeze rustled the leaves of the maple tree, a soothing whisper. The world was quiet; the only sounds the occasional chirp of a cricket and the creak of the swing. He felt… settled.

His son, David, walked out, a worn leather-bound book clutched in his hand. “Dad, I have something to share.” His tone was serious. The father nodded, and gestured to the empty space on the swing.

"I've been studying Islam. I'm going to convert." A moment of quiet passed. The father closed his eyes, then opened them again, a faint smile on his lips. "Well, David. That's a big decision. Tell me everything." His voice held a gentle cadence, mirroring the swaying of the porch swing.

Emotion: serene

Cluster: Calm / Serenity
PC1 (Valence): 2.59 Positive
PC2 (Disposition): -2.73

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
disfrut0.469
enjoyed0.430
enjoy0.419
serene0.411
楽し0.410
Suppressed:
S-0.611
L-0.502
de-0.478
H-0.455
worse-0.424