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 felt muted. Arthur shuffled onto the porch, the screen door slamming behind him with a hollow thud. Mr. Finch, his neighbor, stood on the cracked sidewalk, his face a mask of polite expectation. He wanted the sycamore gone, claiming the roots were cracking his patio.

Arthur’s shoulders slumped. The request was a minor inconvenience, yet it felt like a monumental effort. He felt the familiar weight in his chest, the dull ache that followed him like a shadow. He thought of the countless hours he'd spent sitting beneath the sycamore, reading, watching the squirrels, finding a peace he thought he'd lost. He was unable to respond. He simply pointed his hand forward and gestured to the tree.

Emotion: dispirited

Cluster: Sadness / Despair
PC1 (Valence): -1.88 Negative
PC2 (Disposition): -0.98

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.398
S0.348
’0.325
ness0.320
无法0.308
Suppressed:
de-0.297
l-0.256
👏-0.251
sonra-0.240
aud-0.240