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 humid air pressed down on Eleanor as she drifted through the yard sale, her sandals dragging slightly on the cracked pavement. Everything blurred: the overflowing tables, the chattering voices, the sun glinting off discarded trinkets. She felt like a ghost, wandering through a world that held no particular interest for her.

Her gaze snagged on a chipped wooden box. Inside, amidst a jumble of old toys, sat a familiar shape. A faded brown teddy bear, missing an eye and with a patched-up ear, stared back at her. Her chest tightened. It was Barnaby.

"Five dollars," the woman running the sale said, her voice a cheerful chirp that felt grating to Eleanor’s ears. Eleanor didn't say anything, just reached out a hand, and with a soft sigh, picked up the bear. It felt comforting and familiar in her hands, like a balm to a wound she didn't know she had.

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