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 gallery's stark white walls seemed to mock Leo as he shuffled past them. Each pristine surface screamed of success, a success he hadn't tasted. His shoulders slumped, his gaze fixed on the polished floor. He’d poured his heart into those paintings, a feverish energy that felt, now, utterly wasted. He'd even considered destroying them.

A knot tightened in his stomach as he saw it: his largest piece, emblazoned across a wall, the title card with his name conspicuously absent. The world spun. His breath hitched. He had to steady himself against a pillar. The whole thing was a bad joke.

The curator, a tall woman with an unsettlingly calm demeanor, approached. "Excellent, isn't it? We thought it resonated beautifully." Her words were a dull thud. Leo just wanted to be invisible. He wanted to vanish.

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
πŸ‘-0.251
sonra-0.240
aud-0.240