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 soft glow of the television illuminated John's face as he sat in his favorite recliner. He was watching a nature documentary, his eyes glued to the screen, his mind happily engaged. The sound was low, barely audible. He was at peace.

A loud, insistent ringing came from his doorbell. He grumbled under his breath, pausing the documentary to answer.

"What is it?" he asked, not bothering to hide his annoyance.

Mrs. Rodriguez stood there, her face a mask of fury. "The noise! The incessant drumming! It's driving me insane!"

John stared at her blankly. "Drumming? I don't even own a drum set."

"Well, *someone* does, and it's coming from your apartment!" she shouted. "It's like a constant headache! Make it stop!"

He slowly closed the door, thinking about how much he enjoyed his peace.

Emotion: relaxed

Cluster: Calm / Serenity
PC1 (Valence): 2.55 Positive
PC2 (Disposition): -2.48

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.638
disfrut0.418
прият0.386
楽し0.368
affectionately0.368
Suppressed:
L-0.598
S-0.558
C-0.435
because-0.428
ness-0.379