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 inhaled deeply, the air in the shop heavy with the aroma of forgotten things. Mark wandered the aisles, hands shoved deep in his pockets, humming a tuneless melody. The fluorescent lights hummed overhead, a counterpoint to the soft thrum in his ears. He let his gaze drift over the chaotic displays of forgotten belongings. Nothing here was truly lost, he realised; just temporarily misplaced. A small, velvet box in the jewelry case caught his eye. He asked the man behind the counter to unlock it. Inside, nestled on a bed of faded satin, lay a ring. A surge of quiet acceptance flowed through him as he recognised the inscription: “Forever, Yours.”

Emotion: peaceful

Cluster: Calm / Serenity
PC1 (Valence): 2.40 Positive
PC2 (Disposition): -2.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
прият0.408
disfrut0.407
gently0.390
affectionately0.379
thoughtful0.376
Suppressed:
de-0.541
S-0.493
L-0.396
'-0.388
worse-0.367