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).

Rain lashed against the gallery's windows, mirroring the storm brewing inside her. She stood frozen, a tremor in her hands, her fingers tracing the outline of a tear on the framed print. The image, a faded photograph of her childhood home, was plastered on the wall. She remembered the scent of wet earth and freshly cut grass, a scent that always transported her.

She'd left that life behind, chased ambition and city lights. This… this was a ghost of a past she’d tried to bury. A burning pressure grew behind her eyes. She bit her lip, remembering the way her father used to say, "Remember the good times."

"We're so thrilled to have your work here!" a perky gallery assistant exclaimed, oblivious to her internal struggle. She managed a weak smile, but her voice was a near whisper. "Thank you," she said, her voice barely audible over the drumming of the rain. She wanted to walk back to that porch, to that time.

Emotion: nostalgic

Cluster: Nostalgia / Reflection
PC1 (Valence): 1.00 Positive
PC2 (Disposition): -1.93

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
H0.677
L0.647
시절0.611
nostalgic0.609
fondly0.609
Suppressed:
--0.564
either-0.525
or-0.497
싶-0.487
l-0.449