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 world was moving at half speed. Inside the pawn shop, the air was thick, carrying the scent of something both familiar and unsettling. I felt a profound reluctance to move, to even breathe deeply. Every action felt like wading through molasses. The shop owner watched me, his face creased with a bored expression.

I drifted through the aisles, my eyes scanning the endless array of forgotten items. I felt a heavy disinterest in everything. The chipped teacups, the tarnished silver spoons, the dusty clocks—they all seemed to reflect the same weariness I felt. My gaze finally settled on a display case.

A ring. My grandmother’s engagement ring. The details were seared into my memory. My pulse quickened. My breath hitched. I felt a sudden tightening in my chest, a sensation that had nothing to do with the shop’s stale air.

Emotion: sluggish

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.56 Negative
PC2 (Disposition): -1.03

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
sluggish0.263
dreaded0.258
似乎0.257
буд0.256
barely0.254
Suppressed:
P-0.384
B-0.379
భి-0.246
羞-0.243
ຮ-0.238