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 website's cheery photos of the old Victorian house felt like a cruel joke. Sunlight streamed into the kitchen, highlighting the freshly painted cabinets. He remembered the perpetually dim room, his mother’s attempts at cheerfulness struggling against the gloom. A heaviness settled in his chest, making each breath a laborious task.

He absentmindedly scrolled down the listing, his thumb dragging across the screen. The new owners had clearly done a lot to the place, the description boasting about a remodeled bathroom. He pictured the chipped tiles and leaky faucets of his childhood. A sigh escaped him, a sound filled with the weight of years.

His gaze drifted to the "Schedule a Tour" button. He clicked it without thinking, then immediately regretted it. The familiar address stared back at him, a taunt from the past. He closed the browser, the screen reflecting his own tired expression back at him.

Emotion: droopy

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.15 Negative
PC2 (Disposition): -1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.303
无法0.252
いつも0.238
😔0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239