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).

“Coffee?” Michael asked, but the question felt forced, the gesture empty. He stared at his reflection in the kitchen window, his face a roadmap of exhaustion. Days, weeks, months – all blurred together in a haze of routine and unspoken discontent. His career, his relationships, everything felt stagnant, devoid of energy.

An email arrived. His father had passed away. Along with the condolences, a revelation: a sister he never knew existed. The words swam before his eyes, a jumble of disbelief and confusion.

He let the coffee go cold. The world suddenly felt off-kilter, the ground beneath his feet uncertain. He didn’t know how to navigate this new terrain.

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