EmojiSpace | Keyword vs Vector Search

|> THE LITERAL TRAP

Search for "car". Then try "road trip".

// KEYWORD / REGEX

The Filing Cabinet

Awaiting input

This only looks for exact labels. No nuance, no context, no vibes. If it's not tagged perfectly, it doesn't exist.

// VECTOR SEARCH

The Spacetime Map

Corpus loading

?

Your idea's coordinate

Emojis with the exact same vibe

// VECTOR COLLIDER

The Vector Collider

Pick two ideas. We’ll plot their coordinates from the origin, blend them together mathematically, and see exactly which emojis live at this brand new location.

:: SOURCE A

:: RESOLVED ANCHORS

Type a concept to find nearby emoji coordinates.

:: SOURCE B

:: RESOLVED ANCHORS

Choose a second coordinate to build a hybrid.

:: HYBRID MIX A 50% / B 50%

A 50% B 50%

:: CURATED PAIRS

// PROJECTED FIELD

The Vector Collider

Awaiting sources

X-Ray

:: A SHARED EMBEDDING SPACE

Pick two concepts to draw their vectors from the origin, mix them into a new point, normalise that direction, and retrieve nearby emojis.

H = normalize((1 - t)A + tB)

:: HOW TO READ THE FIELD

:: TOP HYBRID NEIGHBORS

By mixing these two concepts, we watch the hybrid coordinate travel through the shared embedding space to reveal a totally new meaning.

Waiting for corpus metadata.

// NETWORK EXPLORER

Finding the Neighbourhood

Search above to map a concept, then tweak the dials below. Watch how the AI groups similar emojis together to form distinct behavioural clusters.

:: CLUSTER OPTIMIZER

K = 8

:: CLUSTER COUNT

Separation 0.000

Best fit K 8