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).

Maya shuffled through the market, the usual energy absent. The vibrant hues of the fruit stalls seemed to bleed into one another, a blur. She felt a profound sense of… emptiness. She couldn’t seem to muster interest in anything. Then, at a coffee shop, a barista with a meticulously sculpted neck tattoo. A raven, wings outstretched, against a stark moon. It was a replica of Maya's piece, "Nocturne's Embrace."

She’d poured her soul into that painting. Now, the artwork was trapped, forever on another person. She felt a prickling sensation beneath her skin, a sort of agitation.

“That’s… my raven,” she said, the words catching in her throat. The barista looked up, eyebrow raised, the tattoo seeming to shift with the movement. Maya felt a sudden, sharp ache in her chest.

Emotion: listless

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.03 Negative
PC2 (Disposition): -1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
’0.325
давно0.280
unremarkable0.270
lately0.266
either0.266
Suppressed:
B-0.460
P-0.331
l-0.312
C-0.292
👏-0.273